Position innerhalb des Seitenbaumes

Institut für Visualisierung und Interaktive Systeme
Team
Andrés Bruhn

Andrés Bruhn

Herr Prof. Dr.-Ing.

Professor für Intelligente Systeme
Studiendekan
Institut für Visualisierung und Interaktive Systeme (VIS)
Abteilung Computer Vision

Kontakt

+49 711 685 88439
+49 711 685 88340
E-Mail
Website
Visitenkarte (VCF)

Universitätsstraße 38
70569 Stuttgart
Deutschland
Raum: 1.459

Sprechstunde

Friday, 15:45-16:45 (ohne Terminvereinbarung)
Friday, 16:45-17:45 (Studiendekan, mit Terminvereinbarung)

Publikationen

Publikationen:

2024
1. Scheurer, E., Schmalfuss, J., Lis, A., & Bruhn, A. (2024). Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow. In Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE/CVF. https://arxiv.org/abs/2310.17403
  - BibTeX
  - Link
  BibTeX
  @proceedings{scheurer2024detection, author = {Scheurer, Erik and Schmalfuss, Jenny and Lis, Alexander and Bruhn, Andrés}, journal = {Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, publisher = {IEEE/CVF}, title = {Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow}, url = {https://arxiv.org/abs/2310.17403}, year = 2024 }
  Link
  https://arxiv.org/abs/2310.17403
2023
1. Mehl, L., Jahedi, A., Schmalfuss, J., & Bruhn, A. (2023, Januar). M-FUSE: Multi-frame Fusion for Scene Flow Estimation. Proc. Winter Conference on Applications of Computer Vision (WACV). https://doi.org/10.48550/arXiv.2207.05704
  - BibTeX
  - Link
  BibTeX
  @inproceedings{Mehl2023_MFUSE, abstract = {Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically limited to only two frame pairs which does not allow them to exploit temporal information. In our paper we address this shortcoming by proposing a novel multi-frame approach that considers an additional preceding stereo pair. To this end, we proceed in two steps: Firstly, building upon the recent RAFT-3D approach, we develop an improved two-frame baseline by incorporating an advanced stereo method. Secondly, and even more importantly, exploiting the specific modeling concepts of RAFT-3D, we propose a U-Net architecture that performs a fusion of forward and backward flow estimates and hence allows to integrate temporal information on demand. Experiments on the KITTI benchmark do not only show that the advantages of the improved baseline and the temporal fusion approach complement each other, they also demonstrate that the computed scene flow is highly accurate. More precisely, our approach ranks second overall and first for the even more challenging foreground objects, in total outperforming the original RAFT-3D method by more than 16%. Code is available at https://github.com/cv-stuttgart/M-FUSE.}, author = {Mehl, Lukas and Jahedi, Azin and Schmalfuss, Jenny and Bruhn, Andr{\'e}s}, booktitle = {Proc. Winter Conference on Applications of Computer Vision (WACV)}, doi = {10.48550/arXiv.2207.05704}, month = {01}, preprinturl = {https://doi.org/10.48550/arXiv.2207.05704}, title = {M-FUSE: Multi-frame Fusion for Scene Flow Estimation}, url = {https://doi.org/10.48550/arXiv.2207.05704}, year = 2023 }
  Link
  https://doi.org/10.48550/arXiv.2207.05704
2. Mehl, L., Schmalfuss, J., Jahedi, A., Nalivayko, Y., & Bruhn, A. (2023). Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4981–4991. https://openaccess.thecvf.com/content/CVPR2023/html/Mehl_Spring_A_High-Resolution_High-Detail_Dataset_and_Benchmark_for_Scene_Flow_CVPR_2023_paper.html
  - BibTeX
  - Link
  BibTeX
  @inproceedings{Mehl_2023_CVPR, abstract = {While recent methods for motion and stereo estimation recover an unprecedented amount of details, such highly detailed structures are neither adequately reflected in the data of existing benchmarks nor their evaluation methodology. Hence, we introduce Spring -- a large, high-resolution, high-detail, computer-generated benchmark for scene flow, optical flow, and stereo. Based on rendered scenes from the open-source Blender movie "Spring", it provides photo-realistic HD datasets with state-of-the-art visual effects and ground truth training data. Furthermore, we provide a website to upload, analyze and compare results. Using a novel evaluation methodology based on a super-resolved UHD ground truth, our Spring benchmark can assess the quality of fine structures and provides further detailed performance statistics on different image regions. Regarding the number of ground truth frames, Spring is 60x larger than the only scene flow benchmark, KITTI 2015, and 15x larger than the well-established MPI Sintel optical flow benchmark. Initial results for recent methods on our benchmark show that estimating fine details is indeed challenging, as their accuracy leaves significant room for improvement. The Spring benchmark and the corresponding datasets are available at http://spring-benchmark.org.}, author = {Mehl, Lukas and Schmalfuss, Jenny and Jahedi, Azin and Nalivayko, Yaroslava and Bruhn, Andr\'es}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {06}, pages = {4981-4991}, title = {Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo}, url = {https://openaccess.thecvf.com/content/CVPR2023/html/Mehl_Spring_A_High-Resolution_High-Detail_Dataset_and_Benchmark_for_Scene_Flow_CVPR_2023_paper.html}, year = 2023 }
  Link
  https://openaccess.thecvf.com/content/CVPR2023/html/Mehl_Spring_A_High-Resolution_High-Detail_Dataset_and_Benchmark_for_Scene_Flow_CVPR_2023_paper.html
3. Schmalfuss, J., Mehl, L., & Bruhn, A. (2023). Distracting Downpour: Adversarial Weather Attacks for Motion Estimation. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 10106–10116. https://openaccess.thecvf.com/content/ICCV2023/html/Schmalfuss_Distracting_Downpour_Adversarial_Weather_Attacks_for_Motion_Estimation_ICCV_2023_paper.html
  - BibTeX
  - Link
  BibTeX
  @inproceedings{Schmalfuss_2023_ICCV, abstract = {Current adversarial attacks on motion estimation, or optical flow, optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, adverse weather conditions constitute a much more realistic threat scenario. Hence, in this work, we present a novel attack on motion estimation that exploits adversarially optimized particles to mimic weather effects like snowflakes, rain streaks or fog clouds. At the core of our attack framework is a differentiable particle rendering system that integrates particles (i) consistently over multiple time steps (ii) into the 3D space (iii) with a photo-realistic appearance. Through optimization, we obtain adversarial weather that significantly impacts the motion estimation. Surprisingly, methods that previously showed good robustness towards small per-pixel perturbations are particularly vulnerable to adversarial weather. At the same time, augmenting the training with non-optimized weather increases a method's robustness towards weather effects and improves generalizability at almost no additional cost. Our code is available at https://github.com/cv-stuttgart/DistractingDownpour.}, author = {Schmalfuss, Jenny and Mehl, Lukas and Bruhn, Andr\'es}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {10}, pages = {10106-10116}, title = {Distracting Downpour: Adversarial Weather Attacks for Motion Estimation}, url = {https://openaccess.thecvf.com/content/ICCV2023/html/Schmalfuss_Distracting_Downpour_Adversarial_Weather_Attacks_for_Motion_Estimation_ICCV_2023_paper.html}, year = 2023 }
  Link
  https://openaccess.thecvf.com/content/ICCV2023/html/Schmalfuss_Distracting_Downpour_Adversarial_Weather_Attacks_for_Motion_Estimation_ICCV_2023_paper.html
4. Schmalfuss, J., Scheurer, E., Zhao, H., Karantzas, N., Bruhn, A., & Labate, D. (2023). Blind image inpainting with sparse directional filter dictionaries for lightweight CNNs. Journal of Mathematical Imaging and Vision (JMIV), 65, 323–339. https://doi.org/10.1007/s10851-022-01119-6
  - BibTeX
  - Link
  BibTeX
  @article{schmalfuss2022blind, author = {Schmalfuss, Jenny and Scheurer, Erik and Zhao, Heng and Karantzas, Nikolaos and Bruhn, Andres and Labate, Demetrio}, doi = {10.1007/s10851-022-01119-6}, file = {:PDFs/Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs.pdf:PDF;:PDFs/Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs_arxiv.pdf:PDF}, groups = {Inpainting, neural networks, Sparsity, blind inpainting, arXiv}, journal = {Journal of Mathematical Imaging and Vision (JMIV)}, pages = {323-339}, title = {Blind image inpainting with sparse directional filter dictionaries for lightweight {CNNs}}, url = {https://link.springer.com/article/10.1007/s10851-022-01119-6}, volume = 65, year = 2023 }
  Link
  https://link.springer.com/article/10.1007/s10851-022-01119-6
5. Jahedi, A., Luz, M., Rivinius, M., Mehl, L., & Bruhn, A. (2023). MS-RAFT+: High Resolution Multi-Scale RAFT. International Journal of Computer Vision, 1573–1405. https://doi.org/10.1007/s11263-023-01930-7
  - BibTeX
  - Link
  BibTeX
  @article{jahedi2023msraft, abstract = {Hierarchical concepts have proven useful in many classical and learning-based optical flow methods regarding both accuracy and robustness. In this paper we show that such concepts are still useful in the context of recent neural networks that follow RAFT’s paradigm refraining from hierarchical strategies by relying on recurrent updates based on a single-scale all-pairs transform. To this end, we introduce MS-RAFT+: a novel recurrent multi-scale architecture based on RAFT that unifies several successful hierarchical concepts. It employs a coarse-to-fine estimation to enable the use of finer resolutions by useful initializations from coarser scales. Moreover, it relies on RAFT’s correlation pyramid that allows to consider non-local cost information during the matching process. Furthermore, it makes use of advanced multi-scale features that incorporate high-level information from coarser scales. And finally, our method is trained subject to a sample-wise robust multi-scale multi-iteration loss that closely supervises each iteration on each scale, while allowing to discard particularly difficult samples. In combination with an appropriate mixed-dataset training strategy, our method performs favorably. It not only yields highly accurate results on the four major benchmarks (KITTI 2015, MPI Sintel, Middlebury and VIPER), it also allows to achieve these results with a single model and a single parameter setting. Our trained model and code are available at https://github.com/cv-stuttgart/MS_RAFT_plus.}, affiliation = {Jahedi, A; Luz, M (Corresponding Author), Univ Stuttgart, Inst Visualizat & Interact Syst, Stuttgart, Germany. Luz, M (Corresponding Author), Univ Freiburg, Robot Learning Lab, Freiburg, Germany. Jahedi, Azin; Luz, Maximilian; Mehl, Lukas; Bruhn, Andres, Univ Stuttgart, Inst Visualizat & Interact Syst, Stuttgart, Germany. Luz, Maximilian, Univ Freiburg, Robot Learning Lab, Freiburg, Germany. Rivinius, Marc, Univ Stuttgart, Inst Informat Secur, Stuttgart, Germany.}, author = {Jahedi, Azin and Luz, Maximilian and Rivinius, Marc and Mehl, Lukas and Bruhn, Andrés}, doi = {10.1007/s11263-023-01930-7}, issn = {{0920-5691} and {1573-1405}}, journal = {International Journal of Computer Vision}, pages = {1573-1405}, publisher = {Springer}, pubstate = {prepublished}, research-areas = {Computer Science}, title = {MS-RAFT+: High Resolution Multi-Scale RAFT}, unique-id = {WOS:001126025000002}, url = {https://doi.org/10.1007/s11263-023-01930-7}, year = 2023 }
  Link
  https://doi.org/10.1007/s11263-023-01930-7
2022
1. Schmalfuss, J., Mehl, L., & Bruhn, A. (2022). Attacking Motion Estimation with Adversarial Snow. Proc. ECCV Workshop on Adversarial Robustness in the Real World (AROW). https://doi.org/10.48550/arXiv.2210.11242
  - BibTeX
  - Link
  BibTeX
  @inproceedings{schmalfuss2022attacking, abstract = {Current adversarial attacks for motion estimation (optical flow) optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, we exploit a real-world weather phenomenon for a novel attack with adversarially optimized snow. At the core of our attack is a differentiable renderer that consistently integrates photorealistic snowflakes with realistic motion into the 3D scene. Through optimization we obtain adversarial snow that significantly impacts the optical flow while being indistinguishable from ordinary snow. Surprisingly, the impact of our novel attack is largest on methods that previously showed a high robustness to small L_p perturbations. }, author = {Schmalfuss, Jenny and Mehl, Lukas and Bruhn, Andrés}, booktitle = {Proc. ECCV Workshop on Adversarial Robustness in the Real World (AROW)}, doi = {https://doi.org/10.48550/arXiv.2210.11242}, preprinturl = {https://arxiv.org/abs/2210.11242}, title = {Attacking Motion Estimation with Adversarial Snow}, url = {https://arxiv.org/abs/2210.11242}, year = 2022 }
  Link
  https://arxiv.org/abs/2210.11242
2. Krake, T., Bruhn, A., Eberhardt, B., & Weiskopf, D. (2022). Efficient and Robust Background Modeling with Dynamic Mode Decomposition. Journal of Mathematical Imaging and Vision (JMIV), 64, 364–378. https://doi.org/10.1007/s10851-022-01068-0
  - BibTeX
  - Link
  BibTeX
  @article{krake2022efficient, abstract = {A large number of modern video background modeling algorithms deal with computational costly minimization problems that often need parameter adjustments. While in most cases spatial and temporal constraints are added artificially to the minimization process, our approach is to exploit Dynamic Mode Decomposition (DMD), a spectral decomposition technique that naturally extracts spatio-temporal patterns from data. Applied to video data, DMD can compute background models. However, the original DMD algorithm for background modeling is neither efficient nor robust. In this paper, we present an equivalent reformulation with constraints leading to a more suitable decomposition into fore- and background. Due to the reformulation, which uses sparse and low-dimensional structures, an efficient and robust algorithm is derived that computes accurate background models. Moreover, we show how our approach can be extended to RGB data, data with periodic parts, and streaming data enabling a versatile use.}, author = {Krake, Tim and Bruhn, Andrés and Eberhardt, Bernhard and Weiskopf, Daniel}, doi = {10.1007/s10851-022-01068-0}, journal = {Journal of Mathematical Imaging and Vision (JMIV)}, pages = {364-378}, title = {Efficient and Robust Background Modeling with Dynamic Mode Decomposition}, url = {https://link.springer.com/article/10.1007/s10851-022-01068-0}, volume = 64, year = 2022 }
  Link
  https://link.springer.com/article/10.1007/s10851-022-01068-0
3. Schmalfuss, J., Scholze, P., & Bruhn, A. (2022). A perturbation-constrained adversarial attack for evaluating the robustness of optical flow. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Hrsg.), Proc. European Conference on Computer Vision (ECCV) (Bd. 13682, S. 183--200). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-20047-2_11
  - BibTeX
  - Link
  BibTeX
  @inproceedings{schmalfuss2022perturbation, author = {Schmalfuss, Jenny and Scholze, Philipp and Bruhn, Andrés}, booktitle = {Proc. European Conference on Computer Vision (ECCV)}, doi = {10.1007/978-3-031-20047-2_11}, editor = {Avidan, S. and Brostow, G. and Cissé, M. and Farinella, G.M. and Hassner, T.}, isbn = {978-3-031-20047-2}, pages = {183--200}, preprinturl = {https://arxiv.org/abs/2203.13214}, publisher = {Springer Nature Switzerland}, title = {A perturbation-constrained adversarial attack for evaluating the robustness of optical flow}, url = {https://link.springer.com/chapter/10.1007/978-3-031-20047-2_11}, volume = 13682, year = 2022 }
  Link
  https://link.springer.com/chapter/10.1007/978-3-031-20047-2_11
4. Philipp, M., Bacher, N., Sauer, S., Mathis-Ullrich, F., & Bruhn, A. (2022). From Chairs To Brains: Customizing Optical Flow For Surgical Activity Localization. 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 1–5. https://doi.org/10.1109/ISBI52829.2022.9761704
  - BibTeX
  - Link
  BibTeX
  @inproceedings{Philipp_2022, abstract = {Recent approaches for surgical activity localization rely on motion features derived from the optical flow (OF). However, although they consider state-of-the-art CNNs when computing the OF, they typically resort to pre-trained implementations which are domain-unaware. We address this problem in two ways: (i) Using the pre-trained OF-CNN of recent localization approach, we analyze the impact of video properties such as reflections, motion and blur on the quality of the OF from neurosurgical data. (ii) Based on this analysis, we design a specifically tailored synthetic training dataset which allows us to customize the pre-trained OF-CNN for surgical activity localization. Our evaluation clearly shows the benefit of this customization approach. It not only leads to an improved accuracy of the OF itself but, even more importantly, also to an improved performance for the actual localization task.}, author = {Philipp, Markus and Bacher, Neal and Sauer, Stefan and Mathis-Ullrich, Franziska and Bruhn, Andrés}, booktitle = {2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)}, doi = {10.1109/ISBI52829.2022.9761704}, month = {03}, pages = {1–5}, publisher = {IEEE}, title = {From Chairs To Brains: Customizing Optical Flow For Surgical Activity Localization}, url = {https://ieeexplore.ieee.org/document/9761704}, year = 2022 }
  Link
  https://ieeexplore.ieee.org/document/9761704
5. Jahedi, A., Mehl, L., Rivinius, M., & Bruhn, A. (2022). Multi-Scale RAFT: combining hierarchical concepts for learning-based optical flow estimation. IEEE International Conference on Image Processing (ICIP). https://doi.org/10.48550/arXiv.2207.12163
  - BibTeX
  - Link
  BibTeX
  @inproceedings{Jahedi2022_ICIP, abstract = {Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work, we show that multi-scale ideas are still valuable. More precisely, using RAFT as a baseline, we propose a novel multi-scale neural network that combines several hierarchical concepts within a single estimation framework. These concepts include (i) a partially shared coarse-to-fine architecture, (ii) multi-scale features, (iii) a hierarchical cost volume and (iv) a multi-scale multi-iteration loss. Experiments on MPI Sintel and KITTI clearly demonstrate the benefits of our approach. They show not only substantial improvements compared to RAFT, but also state-of-the-art results -- in particular in non-occluded regions.}, author = {Jahedi, Azin and Mehl, Lukas and Rivinius, Marc and Bruhn, Andrés}, booktitle = {IEEE International Conference on Image Processing (ICIP)}, doi = {10.48550/arXiv.2207.12163}, title = {Multi-Scale {RAFT}: combining hierarchical concepts for learning-based optical flow estimation}, url = {/brokenurl# https://doi.org/10.48550/arXiv.2207.12163}, year = 2022 }
  Link
  /brokenurl# https://doi.org/10.48550/arXiv.2207.12163
2021
1. Mehl, L., Beschle, C., Barth, A., & Bruhn, A. (2021). An Anisotropic Selection Scheme for Variational Optical Flow Methods with Order-Adaptive Regularisation. Proceedings of the International Conference on Scale Space and Variational Methods in Computer Vision (SSVM), 140--152. https://doi.org/10.1007/978-3-030-75549-2_12
  - BibTeX
  - Link
  BibTeX
  @inproceedings{10.1007/978-3-030-75549-2_12, abstract = {Approaches based on order-adaptive regularisation belong to the most accurate variational methods for computing the optical flow. By locally deciding between first- and second-order regularisation, they are applicable to scenes with both fronto-parallel and ego-motion. So far, however, existing order-adaptive methods have a decisive drawback. While the involved first- and second-order smoothness terms already make use of anisotropic concepts, the underlying selection process itself is still isotropic in that sense that it locally chooses the same regularisation order for all directions. In our paper, we address this shortcoming. We propose a generalised order-adaptive approach that allows to select the local regularisation order for each direction individually. To this end, we split the order-adaptive regularisation across and along the locally dominant direction and perform an energy competition for each direction separately. This in turn offers another advantage. Since the parameters can be chosen differently for both directions, the approach allows for a better adaption to the underlying scene. Experiments for MPI Sintel and KITTI 2015 demonstrate the usefulness of our approach. They not only show improvements compared to an isotropic selection scheme. They also make explicit that our approach is able to improve the results from state-of-the-art learning-based approaches, if applied as a final refinement step – thereby achieving top results in both benchmarks.}, author = {Mehl, Lukas and Beschle, Cedric and Barth, Andrea and Bruhn, Andrés}, booktitle = {Proceedings of the International Conference on Scale Space and Variational Methods in Computer Vision (SSVM)}, doi = {10.1007/978-3-030-75549-2_12}, pages = {140--152}, publisher = {Springer}, title = {An Anisotropic Selection Scheme for Variational Optical Flow Methods with Order-Adaptive Regularisation}, url = {https://link.springer.com/chapter/10.1007%2F978-3-030-75549-2_12}, year = 2021 }
  Link
  https://link.springer.com/chapter/10.1007%2F978-3-030-75549-2_12
2020
1. Kurzhals, K., Rodrigues, N., Koch, M., Stoll, M., Bruhn, A., Bulling, A., & Weiskopf, D. (2020). Visual Analytics and Annotation of Pervasive Eye Tracking Video. Proceedings of the Symposium on Eye Tracking Research & Applications (ETRA), 16:1-16:9. https://doi.org/10.1145/3379155.3391326
  - BibTeX
  - Link
  BibTeX
  @inproceedings{10.1145/3379155.3391326, abstract = {We propose a new technique for visual analytics and annotation of long-term pervasive eye tracking data for which a combined analysis of gaze and egocentric video is necessary. Our approach enables two important tasks for such data for hour-long videos from individual participants: (1) efficient annotation and (2) direct interpretation of the results. Exemplary time spans can be selected by the user and are then used as a query that initiates a fuzzy search of similar time spans based on gaze and video features. In an iterative refinement loop, the query interface then provides suggestions for the importance of individual features to improve the search results. A multi-layered timeline visualization shows an overview of annotated time spans. We demonstrate the efficiency of our approach for analyzing activities in about seven hours of video in a case study and discuss feedback on our approach from novices and experts performing the annotation task.}, articleno = {16}, author = {Kurzhals, Kuno and Rodrigues, Nils and Koch, Maurice and Stoll, Michael and Bruhn, Andres and Bulling, Andreas and Weiskopf, Daniel}, booktitle = {Proceedings of the Symposium on Eye Tracking Research & Applications (ETRA)}, doi = {10.1145/3379155.3391326}, isbn = {9781450371339}, location = {Stuttgart, Germany}, numpages = {9}, pages = {16:1-16:9}, publisher = {ACM}, title = {Visual Analytics and Annotation of Pervasive Eye Tracking Video}, url = {https://doi.org/10.1145/3379155.3391326}, year = 2020 }
  Link
  https://doi.org/10.1145/3379155.3391326
2. Men, H., Hosu, V., Lin, H., Bruhn, A., & Saupe, D. (2020). Subjective annotation for a frame interpolation benchmark using artefact amplification. Quality and User Experience, 5(1), Article 1. https://doi.org/10.1007/s41233-020-00037-y
  - BibTeX
  - Link
  BibTeX
  @article{Men2020-12Subje-52455, abstract = {Current benchmarks for optical flow algorithms evaluate the estimation either directly by comparing the predicted flow fields with the ground truth or indirectly by using the predicted flow fields for frame interpolation and then comparing the interpolated frames with the actual frames. In the latter case, objective quality measures such as the mean squared error are typically employed. However, it is well known that for image quality assessment, the actual quality experienced by the user cannot be fully deduced from such simple measures. Hence, we conducted a subjective quality assessment crowdscouring study for the interpolated frames provided by one of the optical flow benchmarks, the Middlebury benchmark. It contains interpolated frames from 155 methods applied to each of 8 contents. For this purpose, we collected forced-choice paired comparisons between interpolated images and corresponding ground truth. To increase the sensitivity of observers when judging minute difference in paired comparisons we introduced a new method to the field of full-reference quality assessment, called artefact amplification. From the crowdsourcing data (3720 comparisons of 20 votes each) we reconstructed absolute quality scale values according to Thurstone’s model. As a result, we obtained a re-ranking of the 155 participating algorithms w.r.t. the visual quality of the interpolated frames. This re-ranking not only shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks, the results also provide the ground truth for designing novel image quality assessment (IQA) methods dedicated to perceptual quality of interpolated images. As a first step, we proposed such a new full-reference method, called WAE-IQA, which weights the local differences between an interpolated image and its ground truth.}, author = {Men, Hui and Hosu, Vlad and Lin, Hanhe and Bruhn, Andrés and Saupe, Dietmar}, doi = {10.1007/s41233-020-00037-y}, issn = {2366-0139}, journal = {Quality and User Experience}, note = {Article Number: 8}, number = 1, title = {Subjective annotation for a frame interpolation benchmark using artefact amplification}, url = {https://link.springer.com/article/10.1007%2Fs41233-020-00037-y}, volume = 5, year = 2020 }
  Link
  https://link.springer.com/article/10.1007%2Fs41233-020-00037-y
3. Men, H., Hosu, V., Lin, H., Bruhn, A., & Saupe, D. (2020). Visual Quality Assessment for Interpolated Slow-Motion Videos Based on a Novel Database. Proceedings of the International Conference on Quality of Multimedia Experience (QoMEX), 1–6. https://doi.org/10.1109/QoMEX48832.2020.9123096
  - BibTeX
  - Link
  BibTeX
  @inproceedings{9123096, abstract = {Professional video editing tools can generate slow-motion video by interpolating frames from video recorded at astandard frame rate. Thereby the perceptual quality of such in-terpolated slow-motion videos strongly depends on the underlyinginterpolation techniques. We built a novel benchmark databasethat is specifically tailored for interpolated slow-motion videos(KoSMo-1k). It consists of 1,350 interpolated video sequences,from 30 different content sources, along with their subjectivequality ratings from up to ten subjective comparisons per videopair. Moreover, we evaluated the performance of twelve exist-ing full-reference (FR) image/video quality assessment (I/VQA)methods on the benchmark. In this way, we are able to show thatspecifically tailored quality assessment methods for interpolatedslow-motion videos are needed, since the evaluated methods –despite their good performance on real-time video databases – donot give satisfying results when it comes to frame interpolation.}, author = {Men, H. and Hosu, V. and Lin, H. and Bruhn, A. and Saupe, D.}, booktitle = {Proceedings of the International Conference on Quality of Multimedia Experience (QoMEX)}, doi = {10.1109/QoMEX48832.2020.9123096}, pages = {1-6}, title = {Visual Quality Assessment for Interpolated Slow-Motion Videos Based on a Novel Database}, url = {https://ieeexplore.ieee.org/document/9123096/authors#authors}, year = 2020 }
  Link
  https://ieeexplore.ieee.org/document/9123096/authors#authors
2019
1. Men, H., Lin, H., Hosu, V., Maurer, D., Bruhn, A., & Saupe, D. (2019). Visual Quality Assessment for Motion Compensated Frame Interpolation. Proceedings of the International Conference on Quality of Multimedia Experience (QoMEX), 1–6. https://doi.org/10.1109/QoMEX.2019.8743221
  - BibTeX
  - Link
  BibTeX
  @inproceedings{conf/qomex/MenLHMBS19, abstract = {Current benchmarks for optical flow algorithms evaluate the estimation quality by comparing their predicted flow field with the ground truth, and additionally may compare interpolated frames, based on these predictions, with the correct frames from the actual image sequences. For the latter comparisons, objective measures such as mean square errors are applied. However, for applications like image interpolation, the expected user's quality of experience cannot be fully deduced from such simple quality measures. Therefore, we conducted a subjective quality assessment study by crowdsourcing for the interpolated images provided in one of the optical flow benchmarks, the Middlebury benchmark. We used paired comparisons with forced choice and reconstructed absolute quality scale values according to Thurstone's model using the classical least squares method. The results give rise to a re-ranking of 141 participating algorithms w.r.t. visual quality of interpolated frames mostly based on optical flow estimation. Our re-ranking result shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks.}, author = {Men, Hui and Lin, Hanhe and Hosu, Vlad and Maurer, Daniel and Bruhn, Andrés and Saupe, Dietmar}, booktitle = {Proceedings of the International Conference on Quality of Multimedia Experience (QoMEX)}, doi = {10.1109/QoMEX.2019.8743221}, ee = {https://doi.org/10.1109/QoMEX.2019.8743221}, isbn = {978-1-5386-8212-8}, pages = {1-6}, publisher = {IEEE}, title = {Visual Quality Assessment for Motion Compensated Frame Interpolation}, url = {https://ieeexplore.ieee.org/document/8743221}, year = 2019 }
  Link
  https://ieeexplore.ieee.org/document/8743221
2018
1. Maurer, D., Ju, Y. C., Breuß, M., & Bruhn, A. (2018). Combining Shape from Shading and Stereo: A Joint Variational Method for Estimating Depth, Illumination and Albedo. International Journal of Computer Vision, 126(12), Article 12. https://doi.org/10.1007/s11263-018-1079-1
  - BibTeX
  - Link
  BibTeX
  @article{journals/ijcv/MaurerJBB18, abstract = {Shape from shading (SfS) and stereo are two fundamentally different strategies for image-based 3-D reconstruction. While approaches for SfS infer the depth solely from pixel intensities, methods for stereo are based on a matching process that establishes correspondences across images. This difference in approaching the reconstruction problem yields complementary advantages that are worthwhile being combined. So far, however, most “joint” approaches are based on an initial stereo mesh that is subsequently refined using shading information. In this paper we follow a completely different approach. We propose a joint variational method that combines both cues within a single minimisation framework. To this end, we fuse a Lambertian SfS approach with a robust stereo model and supplement the resulting energy functional with a detail-preserving anisotropic second-order smoothness term. Moreover, we extend the resulting model in such a way that it jointly estimates depth, albedo and illumination. This in turn makes the approach applicable to objects with non-uniform albedo as well as to scenes with unknown illumination. Experiments for synthetic and real-world images demonstrate the benefits of our combined approach: They not only show that our method is capable of generating very detailed reconstructions, but also that joint approaches are feasible in practice.}, author = {Maurer, Daniel and Ju, Yong Chul and Breuß, Michael and Bruhn, Andrés}, doi = {10.1007/s11263-018-1079-1}, ee = {https://doi.org/10.1007/s11263-018-1079-1}, journal = {International Journal of Computer Vision}, number = 12, pages = {1342-1366}, title = {Combining Shape from Shading and Stereo: A Joint Variational Method for Estimating Depth, Illumination and Albedo}, url = {https://doi.org/10.1007/s11263-018-1079-1}, volume = 126, year = 2018 }
  Link
  https://doi.org/10.1007/s11263-018-1079-1
2. Maurer, D., & Bruhn, A. (2018). ProFlow: Learning to Predict Optical Flow. Proceedings of the British Machine Vision Conference (BMVC), 86:1-86:13. https://doi.org/arXiv:1806.00800
  - BibTeX
  - Link
  BibTeX
  @inproceedings{noauthororeditor2018proflow, abstract = {Temporal coherence is a valuable source of information in the context of optical flow estimation. However, finding a suitable motion model to leverage this information is a non-trivial task. In this paper we propose an unsupervised online learning approach based on a convolutional neural network (CNN) that estimates such a motion model individually for each frame. By relating forward and backward motion these learned models not only allow to infer valuable motion information based on the backward flow, they also help to improve the performance at occlusions, where a reliable prediction is particularly useful. Moreover, our learned models are spatially variant and hence allow to estimate non-rigid motion per construction. This, in turns, allows to overcome the major limitation of recent rigidity-based approaches that seek to improve the estimation by incorporating additional stereo/SfM constraints. Experiments demonstrate the usefulness of our new approach. They not only show a consistent improvement of up to 27% for all major benchmarks (KITTI 2012, KITTI 2015, MPI Sintel) compared to a baseline without prediction, they also show top results for the MPI Sintel benchmark -- the one of the three benchmarks that contains the largest amount of non-rigid motion.}, author = {Maurer, Daniel and Bruhn, Andrés}, booktitle = {Proceedings of the British Machine Vision Conference (BMVC)}, doi = {arXiv:1806.00800}, publisher = {BMVA Press}, title = {ProFlow: Learning to Predict Optical Flow}, url = {http://bmvc2018.org/contents/supplementary/pdf/0277_supp.pdf}, volume = {86:1-86:13}, year = 2018 }
  Link
  http://bmvc2018.org/contents/supplementary/pdf/0277_supp.pdf
3. Maurer, D., Marniok, N., Goldluecke, B., & Bruhn, A. (2018). Structure-from-motion-aware PatchMatch for Adaptive Optical Flow Estimation. In V. Ferrari, M. Hebert, C. Sminchisescu, & Y. Weiss (Hrsg.), Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science (Bd. 11212, S. 575–592). Springer International Publishing. https://doi.org/10.1007/978-3-030-01237-3_35
  - BibTeX
  - Link
  BibTeX
  @inbook{conf/eccv/MaurerMGB18, abstract = {Many recent energy-based methods for optical flow estimation rely on a good initialization that is typically provided by some kind of feature matching. So far, however, these initial matching approaches are rather general: They do not incorporate any additional information that could help to improve the accuracy or the robustness of the estimation. In particular, they do not exploit potential cues on the camera poses and the thereby induced rigid motion of the scene. In the present paper, we tackle this problem. To this end, we propose a novel structure-from-motion-aware PatchMatch approach that, in contrast to existing matching techniques, combines two hierarchical feature matching methods: a recent two-frame PatchMatch approach for optical flow estimation (general motion) and a specifically tailored three-frame PatchMatch approach for rigid scene reconstruction (SfM). While the motion PatchMatch serves as baseline with good accuracy, the SfM counterpart takes over at occlusions and other regions with insufficient information. Experiments with our novel SfM-aware PatchMatch approach demonstrate its usefulness. They not only show excellent results for all major benchmarks (KITTI 2012/2015, MPI Sintel), but also improvements up to 50% compared to a PatchMatch approach without structure information.}, author = {Maurer, Daniel and Marniok, Nico and Goldluecke, Bastian and Bruhn, Andrés}, booktitle = {Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science}, doi = {10.1007/978-3-030-01237-3_35}, editor = {Ferrari, Vittorio and Hebert, Martial and Sminchisescu, Cristian and Weiss, Yair}, ee = {https://doi.org/10.1007/978-3-030-01237-3_35}, isbn = {978-3-030-01237-3}, pages = {575-592}, publisher = {Springer International Publishing}, title = {Structure-from-motion-aware PatchMatch for Adaptive Optical Flow Estimation}, url = {https://doi.org/10.1007/978-3-030-01237-3_35 }, volume = 11212, year = 2018 }
  Link
  https://doi.org/10.1007/978-3-030-01237-3_35
4. Maurer, D., Stoll, M., & Bruhn, A. (2018). Directional Priors for Multi-Frame Optical Flow. Proceedings of the British Machine Vision Conference (BMVC), 106:1-106:13. http://bmvc2018.org/contents/papers/0377.pdf
  - BibTeX
  - Link
  BibTeX
  @inproceedings{conf/bmvc/MaurerSB18, abstract = {Pipeline approaches that interpolate and refine an initial set of point correspondenceshave recently shown a good performance in the field of optical flow estimation. However,so far, these methods are typically restricted to two frames which makes exploiting tem-poral information difficult. In this paper, we show how such pipeline approaches can beextended to the temporal domain and how directional constraints can be incorporated tofurther improve the estimation. To this end, we not only suggest to exploit temporal infor-mation in the prefiltering step, we also propose a trajectorial refinement method that liftssuccessful concepts of recent variational two-frame methods to the multi-frame domain.Experiments demonstrate the usefulness of our pipeline approach. They do not only showgood results in general, they also demonstrate the clear benefits of using multiple framesand of imposing directional constraints on the prefiltering step and the refinement.}, author = {Maurer, Daniel and Stoll, Michael and Bruhn, Andrés}, booktitle = {Proceedings of the British Machine Vision Conference (BMVC)}, crossref = {conf/bmvc/2018}, ee = {http://bmvc2018.org/contents/papers/0377.pdf}, pages = {106:1-106:13}, publisher = {BMVA Press}, title = {Directional Priors for Multi-Frame Optical Flow}, url = {http://bmvc2018.org/contents/papers/0377.pdf}, year = 2018 }
  Link
  http://bmvc2018.org/contents/papers/0377.pdf
2017
1. Stoll, M., Maurer, D., Volz, S., & Bruhn, A. (2017). Illumination-Aware Large Displacement Optical Flow. In E. Hancock & M. Pelillo (Hrsg.), Proceedings of International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR). Lecture Notes in Computer Science. Springer.
  - BibTeX
  BibTeX
  @inproceedings{d7910e5a7878417aaddc8b3c8891b40b, author = {Stoll, Michael and Maurer, Daniel and Volz, Sebastian and Bruhn, Andrés}, booktitle = {Proceedings of International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR). Lecture Notes in Computer Science}, editor = {Hancock, E. and Pelillo, M.}, publisher = {Springer}, title = {Illumination-Aware Large Displacement Optical Flow}, year = 2017 }
2. Kurzhals, K., Stoll, M., Bruhn, A., & Weiskopf, D. (2017). FlowBrush: Optical Flow Art. Proceedings of Computational Aesthetics 2017. http://dx.doi.org/10.1145/3092912.3092914
  - BibTeX
  - Link
  BibTeX
  @inproceedings{aea7916dcac7402d87b595c395074a8b, author = {Kurzhals, Kuno and Stoll, Michael and Bruhn, Andrés and Weiskopf, Daniel}, booktitle = {Proceedings of Computational Aesthetics 2017}, privnote = {uid:2390}, title = {FlowBrush: Optical Flow Art}, url = {http://dx.doi.org/10.1145/3092912.3092914}, year = 2017 }
  Link
  http://dx.doi.org/10.1145/3092912.3092914
3. Maurer, D., Bruhn, A., & Stoll, M. (2017). Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement. Proceedings of the British Machine Vision Conference (BMVC).
  - BibTeX
  BibTeX
  @inproceedings{bc819c3f13034a82bb8023234baa091b, author = {Maurer, Daniel and Bruhn, Andrés and Stoll, Michael}, booktitle = {Proceedings of the British Machine Vision Conference (BMVC)}, privnote = {uid:2395}, publisher = {BMVA Press}, title = {Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement}, year = 2017 }
4. Maurer, D., Stoll, M., & Bruhn, A. (2017). Order-adaptive Regularisation for Variational Optical Flow: Global, Local and in Between. In F. Lauze, Y. Dong, & A. B. Dahl (Hrsg.), Scale Space and Variational Methods in Computer Vision. SSVM 2017. Lecture Notes in Computer Science (Bd. 10302, S. 550–562). Springer International Publishing. https://doi.org/10.1007/978-3-319-58771-4_44
  - BibTeX
  - Link
  BibTeX
  @inproceedings{conf/scalespace/MaurerSB17, abstract = {Recent approaches for variational motion estimation typically either rely on first or second order regularisation strategies. While first order strategies are more appropriate for scenes with fronto-parallel motion, second order constraints are superior if it comes to the estimation of affine flow fields. Since using the wrong regularisation order may lead to a significant deterioration of the results, it is surprising that there has not been much effort in the literature so far to determine this order automatically. In our work, we address the aforementioned problem in two ways. (i) First, we discuss two anisotropic smoothness terms of first and second order, respectively, that share important structural properties and that are thus particularly suited for being combined within an order-adaptive variational framework. (ii) Secondly, based on these two smoothness terms, we develop four different variational methods and with it four different strategies for adaptively selecting the regularisation order: a global and a local strategy based on half-quadratic regularisation, a non-local approach that relies on neighbourhood information, and a region based method using level sets. Experiments on recent benchmarks show the benefits of each of the strategies. Moreover, they demonstrate that adaptively combining different regularisation orders not only allows to outperform single-order strategies but also to obtain advantages beyond the ones of a frame-wise selection.}, author = {Maurer, Daniel and Stoll, Michael and Bruhn, Andrés}, booktitle = {Scale Space and Variational Methods in Computer Vision. SSVM 2017. Lecture Notes in Computer Science}, doi = {10.1007/978-3-319-58771-4_44}, editor = {Lauze, François and Dong, Yiqiu and Dahl, Anders Bjorholm}, ee = {https://doi.org/10.1007/978-3-319-58771-4_44}, isbn = {978-3-319-58771-4}, pages = {550-562}, publisher = {Springer International Publishing}, title = {Order-adaptive Regularisation for Variational Optical Flow: Global, Local and in Between.}, url = {https://doi.org/10.1007/978-3-319-58771-4_44}, volume = 10302, year = 2017 }
  Link
  https://doi.org/10.1007/978-3-319-58771-4_44
5. Stoll, M., Maurer, D., & Bruhn, A. (2017). Variational Large Displacement Optical Flow Without Feature Matches. In M. Pelillo & E. R. Hancock (Hrsg.), Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2017. Lecture Notes in Computer Science (Bd. 10746, S. 79–92). Springer International Publishing. https://doi.org/10.1007/978-3-319-78199-0_6
  - BibTeX
  - Link
  BibTeX
  @inproceedings{conf/emmcvpr/StollMB17, abstract = {The optical flow within a scene can be an arbitrarily complex composition of motion patterns that typically differ regarding their scale. Hence, using a single algorithm with a single set of parameters is often not sufficient to capture the variety of these motion patterns. In particular, the estimation of large displacements of small objects poses a problem. In order to cope with this problem, many recent methods estimate the optical flow by a fusion of flow candidates obtained either from different algorithms or from the same algorithm using different parameters. This, however, typically results in a pipeline of methods for estimating and fusing the candidate flows, each requiring an individual model with a dedicated solution strategy. In this paper, we investigate what results can be achieved with a pure variational approach based on a standard coarse-to-fine optimization. To this end, we propose a novel variational method for the simultaneous estimation and fusion of flow candidates. By jointly using multiple smoothness weights within a single energy functional, we are able to capture different motion patterns and hence to estimate large displacements even without additional feature matches. In the same functional, an intrinsic model-based fusion allows to integrate all these candidates into a single flow field, combining sufficiently smooth overall motion with locally large displacements. Experiments on large displacement sequences and the Sintel benchmark demonstrate the feasibility of our approach and show improved results compared to a single-smoothness baseline method.}, author = {Stoll, Michael and Maurer, Daniel and Bruhn, Andrés}, booktitle = { Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2017. Lecture Notes in Computer Science}, doi = {10.1007/978-3-319-78199-0_6}, editor = {Pelillo, Marcello and Hancock, Edwin R.}, ee = {https://doi.org/10.1007/978-3-319-78199-0_6}, isbn = {978-3-319-78199-0}, pages = {79-92}, publisher = {Springer International Publishing}, title = {Variational Large Displacement Optical Flow Without Feature Matches.}, url = {https://doi.org/10.1007/978-3-319-78199-0_6}, volume = 10746, year = 2017 }
  Link
  https://doi.org/10.1007/978-3-319-78199-0_6
6. Maurer, D., Stoll, M., Volz, S., Gairing, P., & Bruhn, A. (2017). A Comparison of Isotropic and Anisotropic Second Order Regularisers for Optical Flow. In F. Lauze, Y. Dong, & A. B. Dahl (Hrsg.), Scale Space and Variational Methods in Computer Vision. SSVM 2017. Lecture Notes in Computer Science (Bd. 10302, S. 537–549). Springer International Publishing. https://doi.org/10.1007/978-3-319-58771-4_43
  - BibTeX
  - Link
  BibTeX
  @inbook{conf/scalespace/MaurerSVGB17, author = {Maurer, Daniel and Stoll, Michael and Volz, Sebastian and Gairing, Patrick and Bruhn, Andrés}, booktitle = {Scale Space and Variational Methods in Computer Vision. SSVM 2017. Lecture Notes in Computer Science}, doi = {10.1007/978-3-319-58771-4_43}, editor = {Lauze, François and Dong, Yiqiu and Dahl, Anders Bjorholm}, ee = {https://doi.org/10.1007/978-3-319-58771-4_43}, isbn = {978-3-319-58771-4}, pages = {537-549}, publisher = {Springer International Publishing}, title = {A Comparison of Isotropic and Anisotropic Second Order Regularisers for Optical Flow}, url = {https://doi.org/10.1007/978-3-319-58771-4_43}, volume = 10302, year = 2017 }
  Link
  https://doi.org/10.1007/978-3-319-58771-4_43
7. Stoll, M., Volz, S., Maurer, D., & Bruhn, A. (2017). A Time-Efficient Optimisation Framework for Parameters of Opitical Flow Methods. In R. Jenssen, P. Sharma, & F. M. Bianchi (Hrsg.), Proceedings of Scandinavian Conference on Image Analysis (SCIA). Lecture Notes in Computer Science (Bd. 10269). Springer.
  - BibTeX
  BibTeX
  @inproceedings{008e9cd783b44dbeba802331440d7f1e, author = {Stoll, Michael and Volz, Sebastian and Maurer, Daniel and Bruhn, Andrés}, booktitle = {Proceedings of Scandinavian Conference on Image Analysis (SCIA). Lecture Notes in Computer Science}, editor = {Jenssen, R. and Sharma, P. and Bianchi, F. M.}, privnote = {uid:2398}, publisher = {Springer}, title = {A Time-Efficient Optimisation Framework for Parameters of Opitical Flow Methods}, volume = 10269, year = 2017 }
2016
1. Ju, Y.-C., Maurer, D., Breuß, M., & Bruhn, A. (2016). Direct Variational Perspective Shape from Shading with Cartesian Depth Parametrisation. In M. Breuß, P. Maragos, & S. Wuhrer (Hrsg.), Perspectives on Shape From Shading. Mathematics and Visualization. Springer.
  - BibTeX
  BibTeX
  @inbook{fcb8069f2bf44b9e9dac261ae0c667b6, author = {Ju, Yong-Chul and Maurer, Daniel and Breuß, Michael and Bruhn, Andrés}, booktitle = {Perspectives on Shape From Shading. Mathematics and Visualization}, editor = {Breuß, M. and Maragos, P. and Wuhrer, S.}, privnote = {uid:2135}, publisher = {Springer}, title = {Direct Variational Perspective Shape from Shading with Cartesian Depth Parametrisation}, year = 2016 }
2. Weickert, J., Grewenig, S., Schroers, C., & Bruhn, A. (2016). Cyclic Schemes for PDE-based Image Analysis. International Journal of Computer Vision, 118(3), Article 3.
  - BibTeX
  BibTeX
  @article{26bfad53366d432195dfc10bbc199b9e, author = {Weickert, Joachim and Grewenig, Sven and Schroers, Christopher and Bruhn, Andrés}, journal = {International Journal of Computer Vision}, number = 3, privnote = {uid:2136}, title = {Cyclic Schemes for PDE-based Image Analysis}, volume = 118, year = 2016 }
3. Maurer, D., Ju, Y.-C., Breuß, M., & Bruhn, A. (2016). Combining shape from shading and stereo: a variational approach for the joint estimation of depth, illumination and albedo. Proceedings of the British Machine Vision Conference (BMVC).
  - BibTeX
  BibTeX
  @inproceedings{b45aa68a780d40d3a048e310f4ca89e3, author = {Maurer, Daniel and Ju, Yong-Chul and Breuß, Michael and Bruhn, Andrés}, booktitle = {Proceedings of the British Machine Vision Conference (BMVC)}, privnote = {uid:2341}, publisher = {BMVA Press}, title = {Combining shape from shading and stereo: a variational approach for the joint estimation of depth, illumination and albedo.}, year = 2016 }
2015
1. Maurer, D., Ju, Y.-C., Breuß, M., & Bruhn, A. (2015). An Efficient Linearisation Approach for Variational Perspective Shape from Shading. In J. Gall, P. Gehler, & B. Leibe (Hrsg.), German Conference on Pattern Recognition (GCPR 2015). Lecture Notes in Computer Science (Bd. 9358). Springer. http://dx.doi.org/10.1007/978-3-319-24947-6_20
  - BibTeX
  - Link
  BibTeX
  @inproceedings{4a1f5015d0624c3b98d5bcad8f33be03, author = {Maurer, Daniel and Ju, Yong-Chul and Breuß, Michael and Bruhn, Andrés}, booktitle = {German Conference on Pattern Recognition (GCPR 2015). Lecture Notes in Computer Science}, editor = {Gall, J. and Gehler, P. and Leibe, B.}, privnote = {uid:2134}, publisher = {Springer}, title = {An Efficient Linearisation Approach for Variational Perspective Shape from Shading}, url = {http://dx.doi.org/10.1007/978-3-319-24947-6_20}, volume = 9358, year = 2015 }
  Link
  http://dx.doi.org/10.1007/978-3-319-24947-6_20
2. Ju, Y.-C., Breuß, M., & Bruhn, A. (2015). Variational Perspective Shape from Shading. In J.-F. Aujol, M. Nikolova, & N. Papadakis (Hrsg.), Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2015). Lecture Notes in Computer Science. Springer.
  - BibTeX
  BibTeX
  @inproceedings{d12e1c91ec154d7fb71d9dfb4fb474b6, author = {Ju, Yong-Chul and Breuß, Michael and Bruhn, Andrés}, booktitle = {Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2015). Lecture Notes in Computer Science}, editor = {Aujol, J.-F. and Nikolova, M. and Papadakis, N.}, privnote = {uid:2034}, publisher = {Springer}, title = {Variational Perspective Shape from Shading}, year = 2015 }
3. Bruhn, A., Imiya, A., Leonardis, A., & Pajdla, T. (2015). Vision for Autonomous Vehicles and Probes (Dagstuhl Seminar 15461). Dagstuhl Reports 5(11): 36-61.
  - BibTeX
  BibTeX
  @techreport{5633f840e2a243d5aa578b75e7b9deaa, author = {Bruhn, Andrés and Imiya, Atsushi and Leonardis, Ales and Pajdla, Tomas}, institution = { Dagstuhl Reports 5(11): 36-61}, privnote = {uid:2250}, title = {Vision for Autonomous Vehicles and Probes (Dagstuhl Seminar 15461).}, year = 2015 }
2014
1. Demetz, O., Stoll, M., Volz, S., Weickert, J., & Bruhn, A. (2014). Learning Brightness Transfer Functions for the Joint Recovery of Illumination Changes and Optical Flow. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Hrsg.), Proceedings of European Conference on Computer Vision (ECCV 2014). Lecture Notes in Computer Science (Bd. 8689). Springer. http://dx.doi.org/10.1007/978-3-319-10590-1_30
  - BibTeX
  - Link
  BibTeX
  @inproceedings{f39917c60df24a999093aef70ee6cb0e, author = {Demetz, Oliver and Stoll, Michael and Volz, Sebastian and Weickert, Joachim and Bruhn, Andrés}, booktitle = {Proceedings of European Conference on Computer Vision (ECCV 2014). Lecture Notes in Computer Science}, editor = {Fleet, D. and Pajdla, T. and Schiele, B. and Tuytelaars, T.}, privnote = {uid:1928}, publisher = {Springer}, title = {Learning Brightness Transfer Functions for the Joint Recovery of Illumination Changes and Optical Flow}, url = {http://dx.doi.org/10.1007/978-3-319-10590-1_30}, volume = 8689, year = 2014 }
  Link
  http://dx.doi.org/10.1007/978-3-319-10590-1_30
2. Bruhn, A., Pock, T., & Tai, X.-C. (Eds. ). (2014). Efficient Algorithms for Global Optimisation Problems in Computer Vision, LNCS 8293. In A. Kuiijper, T. Pock, K. Bredies, & H. Bischof (Hrsg.), Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2013). Lecture Notes in Computer Science (8293. Aufl.). Springer.
  - BibTeX
  BibTeX
  @book{6649c8db7fa441cfa0c55fb7993f2e27, author = {Bruhn, Andrés and Pock, Thomas and Tai, Xue-Cheng (Eds.)}, booktitle = {Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2013). Lecture Notes in Computer Science}, edition = 8293, editor = {Kuiijper, A. and Pock, T. and Bredies, K. and Bischof, H.}, privnote = {uid:1834}, publisher = {Springer}, title = {Efficient Algorithms for Global Optimisation Problems in Computer Vision, LNCS 8293}, year = 2014 }
3. Schmaltz, C., Peter, P., Mainberger, M., Ebel, F., Weickert, J., & Bruhn, A. (2014). Understanding, optimising, and extending data compression with anisotropic diffusion. International Journal of Computer Vision, 108(3), Article 3. http://dx.doi.org/10.1007/s11263-014-0702-z
  - BibTeX
  - Link
  BibTeX
  @article{c17f3e48d49949c7a8afac9dd10b1b03, author = {Schmaltz, Christian and Peter, Pascal and Mainberger, Markus and Ebel, Franziska and Weickert, Joachim and Bruhn, Andrés}, journal = {International Journal of Computer Vision}, number = 3, privnote = {uid:1854}, title = {Understanding, optimising, and extending data compression with anisotropic diffusion}, url = {http://dx.doi.org/10.1007/s11263-014-0702-z}, volume = 108, year = 2014 }
  Link
  http://dx.doi.org/10.1007/s11263-014-0702-z
2013
1. Persch, N., Elhayek, A., Welk, M., Bruhn, A., Grewenig, S., Böse, K., Kraegeloh, A., & Weickert, J. (2013). Enhancing 3-D cell structures in confocal and STED microscopy: a joint model for interpolation, deblurring and anistropic smoothing. Measurement Science and Technology, 24(12), Article 12. http://dx.doi.org/10.1088/0957-0233/24/12/125703
  - BibTeX
  - Link
  BibTeX
  @article{d2325745b9e84d4eb4b5062a5059279b, author = {Persch, Nico and Elhayek, Ahmed and Welk, Martin and Bruhn, Andrés and Grewenig, Sven and Böse, Katharina and Kraegeloh, Annette and Weickert, Joachim}, journal = {Measurement Science and Technology}, number = 12, privnote = {uid:1812}, title = {Enhancing 3-D cell structures in confocal and STED microscopy: a joint model for interpolation, deblurring and anistropic smoothing}, url = {http://dx.doi.org/10.1088/0957-0233/24/12/125703}, volume = 24, year = 2013 }
  Link
  http://dx.doi.org/10.1088/0957-0233/24/12/125703
2. Stoll, M., Volz, S., & Bruhn, A. (2013). Joint trilateral filtering for multiframe optical flow. In I. C. S. Press (Hrsg.), Proceedings of IEEE International Conference on Image Processing (ICIP 2013) (Bd. 2013). IEEE Computer Society Press. http://dx.doi.org/10.1109/ICIP.2013.6738792
  - BibTeX
  - Link
  BibTeX
  @inproceedings{a9737f60218a4499bd2b0c34d917c5bc, author = {Stoll, Michael and Volz, Sebastian and Bruhn, Andrés}, booktitle = {Proceedings of IEEE International Conference on Image Processing (ICIP 2013)}, editor = {Press, IEEE Computer Society}, privnote = {uid:1688}, publisher = {IEEE Computer Society Press}, title = {Joint trilateral filtering for multiframe optical flow}, url = {http://dx.doi.org/10.1109/ICIP.2013.6738792}, volume = 2013, year = 2013 }
  Link
  http://dx.doi.org/10.1109/ICIP.2013.6738792
3. Stoll, M., Krüger, R., Ertl, T., & Bruhn, A. (2013). Racecar Tracking and its Visualization Using Sparse Data. 1st IEEE VIS Workshop on Sports Data Visualization, 2013.
  - BibTeX
  BibTeX
  @inproceedings{7eb5bc45a83e4c8bb30fb15342a9b82c, author = {Stoll, Michael and Krüger, Robert and Ertl, Thomas and Bruhn, Andrés}, booktitle = {1st IEEE VIS Workshop on Sports Data Visualization}, privnote = {uid:1757}, title = {Racecar Tracking and its Visualization Using Sparse Data}, volume = 2013, year = 2013 }
4. Ju, Y.-C., Tozza, S., Breuß, M., Bruhn, A., & Kleefeld, A. (2013). Generalised perspective shape from shading with Oren-Nayar reflectance. Proceedings of the British Machine Vision Conference (BMVC). http://dx.doi.org/10.5244/C.27.42
  - BibTeX
  - Link
  BibTeX
  @inproceedings{ec586cef3598433da915550f8fbfe61e, author = {Ju, Yong-Chul and Tozza, Siliva and Breuß, Michael and Bruhn, Andrés and Kleefeld, Andreas}, booktitle = {Proceedings of the British Machine Vision Conference (BMVC)}, privnote = {uid:1811}, publisher = {BMVA Press}, title = {Generalised perspective shape from shading with Oren-Nayar reflectance.}, url = {http://dx.doi.org/10.5244/C.27.42}, year = 2013 }
  Link
  http://dx.doi.org/10.5244/C.27.42
5. Stoll, M., Volz, S., & Bruhn, A. (2013). Adaptive integration of feature matches into variational optical flow methods. In K. M. Lee, J. Rehg, Y. Matsushita, & Z. Hu (Hrsg.), Proceedings of Asian Conference on Computer Vision (ACCV 2012). Lecture Notes in Computer Science. Springer. http://dx.doi.org/10.1007/978-3-642-37431-9_1
  - BibTeX
  - Link
  BibTeX
  @inproceedings{a3fa047626774b4da4716c75e0333e76, author = {Stoll, Michael and Volz, Sebastian and Bruhn, Andrés}, booktitle = {Proceedings of Asian Conference on Computer Vision (ACCV 2012). Lecture Notes in Computer Science}, editor = {Lee, K. M. and Rehg, J. and Matsushita, Y. and Hu, Z.}, privnote = {uid:1488}, publisher = {Springer}, title = {Adaptive integration of feature matches into variational optical flow methods}, url = {http://dx.doi.org/10.1007/978-3-642-37431-9_1}, year = 2013 }
  Link
  http://dx.doi.org/10.1007/978-3-642-37431-9_1
6. Galliani, S., Ju, Y.-C., Breuß, M., & Bruhn, A. (2013). Generalised perspective shape from shading in spherical coordinates. In A. Kuiijper, T. Pock, K. Bredies, & H. Bischof (Hrsg.), Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2013). Lecture Notes in Computer Science. Springer. http://dx.doi.org/10.1007/978-3-642-38267-3_19
  - BibTeX
  - Link
  BibTeX
  @inproceedings{62ff05cb102c472a9c405e4adcc77110, author = {Galliani, Silvano and Ju, Yong-Chul and Breuß, Michael and Bruhn, Andrés}, booktitle = {Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2013). Lecture Notes in Computer Science}, editor = {Kuiijper, A. and Pock, T. and Bredies, K. and Bischof, H.}, privnote = {uid:1613}, publisher = {Springer}, title = {Generalised perspective shape from shading in spherical coordinates}, url = {http://dx.doi.org/10.1007/978-3-642-38267-3_19}, year = 2013 }
  Link
  http://dx.doi.org/10.1007/978-3-642-38267-3_19
2012
1. Demetz, O., Weickert, J., Bruhn, A., & Zimmer, H. (2012). Optic flow scale space. In A. Bruckstein, B. ter Haar Romeny, A. Bronstein, & M. Bronstein (Hrsg.), Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2011). Lecture Notes in Computer Science (Bd. 6667). Springer. http://dx.doi.org/10.1007/3-540-63931-4_268
  - BibTeX
  - Link
  BibTeX
  @inproceedings{4bd4a5c970df4e349fd72aa97d120b34, author = {Demetz, Oliver and Weickert, Joachim and Bruhn, Andrés and Zimmer, Henning}, booktitle = {Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2011). Lecture Notes in Computer Science}, editor = {Bruckstein, A. and ter Haar Romeny, B. and Bronstein, A. and Bronstein, M.}, privnote = {uid:1318}, publisher = {Springer}, title = {Optic flow scale space}, url = {http://dx.doi.org/10.1007/3-540-63931-4_268}, volume = 6667, year = 2012 }
  Link
  http://dx.doi.org/10.1007/3-540-63931-4_268
2. Ju, Y.-C., Breuß, M., Bruhn, A., & Galliani, S. (2012). Shape from Shading for Rough Surfaces: Analysis of the Oren-Nayar Model. Proceedings of the British Machine Vision Conference (BMVC). http://dx.doi.org/10.5244/C.26.104
  - BibTeX
  - Link
  BibTeX
  @inproceedings{181f5af027cf457d8512e3754d35ac5f, author = {Ju, Yong-Chul and Breuß, Michael and Bruhn, Andrés and Galliani, Silvano}, booktitle = {Proceedings of the British Machine Vision Conference (BMVC)}, privnote = {uid:1433}, publisher = {BMVA Press}, title = {Shape from Shading for Rough Surfaces: Analysis of the Oren-Nayar Model}, url = {http://dx.doi.org/10.5244/C.26.104}, year = 2012 }
  Link
  http://dx.doi.org/10.5244/C.26.104
3. Valgaerts, L., Bruhn, A., Mainberger, M., & Weickert, J. (2012). Dense versus sparse approaches for estimating the fundamental matrix. International Journal of Computer Vision, 96(2), Article 2. http://dx.doi.org/10.1007/s11263-011-0466-7
  - BibTeX
  - Link
  BibTeX
  @article{00bf3435c24344ffb68e377c202aa537, author = {Valgaerts, Levi and Bruhn, Andrés and Mainberger, Markus and Weickert, Joachim}, journal = {International Journal of Computer Vision}, number = 2, privnote = {uid:1302}, title = {Dense versus sparse approaches for estimating the fundamental matrix}, url = {http://dx.doi.org/10.1007/s11263-011-0466-7}, volume = 96, year = 2012 }
  Link
  http://dx.doi.org/10.1007/s11263-011-0466-7
4. Schroers, C., Zimmer, H., Valgaerts, L., Bruhn, A., Demetz, O., & Weickert, J. (2012). Anisotropic range image integration. Awarded a DAGM-OAGM 2012 Paper Prize. In A. Pinz, T. Pock, H. Bischof, & F. Leberl (Hrsg.), Proceedings of German and Austrian Pattern Recognition Symposium (DAGM-OAGM 2012). Lecture Notes in Computer Science (Bd. 7476). Springer. http://dx.doi.org/10.1007/978-3-642-32717-9_8
  - BibTeX
  - Link
  BibTeX
  @inproceedings{f6b0e4313b674dde8c386602dce60ee8, author = {Schroers, Christopher and Zimmer, Henning and Valgaerts, Levi and Bruhn, Andrés and Demetz, Oliver and Weickert, Joachim}, booktitle = {Proceedings of German and Austrian Pattern Recognition Symposium (DAGM-OAGM 2012). Lecture Notes in Computer Science}, editor = {Pinz, A. and Pock, T. and Bischof, H. and Leberl, F.}, privnote = {uid:1432}, publisher = {Springer}, title = {Anisotropic range image integration. Awarded a DAGM-OAGM 2012 Paper Prize}, url = {http://dx.doi.org/10.1007/978-3-642-32717-9_8}, volume = 7476, year = 2012 }
  Link
  http://dx.doi.org/10.1007/978-3-642-32717-9_8
5. Gwosdek, P., Grewenig, S., Bruhn, A., & Weickert, J. (2012). Theoretical foundations of Gaussian convolution by extended box filtering. In A. Bruckstein, B. ter Haar Romeny, A. Bronstein, & M. Bronstein (Hrsg.), Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2011). Lecture Notes in Computer Science (Bd. 6667). Springer. http://dx.doi.org/10.1007/978-3-642-24785-9_38
  - BibTeX
  - Link
  BibTeX
  @inproceedings{3245b9d4206f4f7f8b9872900c0a061e, author = {Gwosdek, Pascal and Grewenig, Sven and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2011). Lecture Notes in Computer Science}, editor = {Bruckstein, A. and ter Haar Romeny, B. and Bronstein, A. and Bronstein, M.}, privnote = {uid:1319}, publisher = {Springer}, title = {Theoretical foundations of Gaussian convolution by extended box filtering}, url = {http://dx.doi.org/10.1007/978-3-642-24785-9_38}, volume = 6667, year = 2012 }
  Link
  http://dx.doi.org/10.1007/978-3-642-24785-9_38
6. Lau Raket, L., Roholm, L., Bruhn, A., & Weickert, J. (2012). Motion compensated frame interpolation with a symmetrical optical flow constraint. In B. George, B. Richard, K. Darko, & P. Bharam (Hrsg.), Proceedings of International Symposium on Visual Computing (ISVC 2012). Lecture Notes in Computer Science (Bd. 7431). Springer. http://dx.doi.org/10.1007/978-3-642-33179-4_43
  - BibTeX
  - Link
  BibTeX
  @inproceedings{109f024d60e54dcab62a820b3255b1f7, author = {Lau Raket, Lars and Roholm, Lars and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of International Symposium on Visual Computing (ISVC 2012). Lecture Notes in Computer Science}, editor = {George, B. and Richard, B. and Darko, K. and Bharam, P.}, privnote = {uid:1380}, publisher = {Springer}, title = {Motion compensated frame interpolation with a symmetrical optical flow constraint}, url = {http://dx.doi.org/10.1007/978-3-642-33179-4_43}, volume = 7431, year = 2012 }
  Link
  http://dx.doi.org/10.1007/978-3-642-33179-4_43
7. Valgaerts, L., Wu, C., Bruhn, A., Seidel, H.-P., & Theobalt, C. (2012). Lightweight Binocular Facial Performance Capture under Uncontrolled Lighting. ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 31(6), Article 6. http://dx.doi.org/10.1145/2366145.2366206
  - BibTeX
  - Link
  BibTeX
  @article{53dea6490c2642ecaecf5d4ca1f50b50, author = {Valgaerts, Levi and Wu, Chenglei and Bruhn, Andrés and Seidel, Hans-Peter and Theobalt, Christian}, journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)}, number = 6, privnote = {uid:1474}, title = {Lightweight Binocular Facial Performance Capture under Uncontrolled Lighting}, url = {http://dx.doi.org/10.1145/2366145.2366206}, volume = 31, year = 2012 }
  Link
  http://dx.doi.org/10.1145/2366145.2366206
2011
1. Bruhn, A., Imiya, A., Leonardis, A., & Pajdla, T. (2011). Efficient Algorithms for Global Optimisation Methods in Computer Vision (Dagstuhl Seminar 11471). Dagstuhl Reports 1(11): 66-90.
  - BibTeX
  BibTeX
  @techreport{ce82a8e37d38470b98f48452ffd421e2, author = {Bruhn, Andrés and Imiya, Atsushi and Leonardis, Ales and Pajdla, Tomas}, institution = { Dagstuhl Reports 1(11): 66-90}, privnote = {uid:2251}, title = {Efficient Algorithms for Global Optimisation Methods in Computer Vision (Dagstuhl Seminar 11471).}, year = 2011 }
2. Mainberger, M., Bruhn, A., Weickert, J., & Forchhammer, S. (2011). Edge-based compression of cartoon-like images with homogeneous diffusion. Pattern Recognition, 44(9), Article 9.
  - BibTeX
  BibTeX
  @article{ec1083842497415faa57e5eff80622e4, author = {Mainberger, Markus and Bruhn, Andrés and Weickert, Joachim and Forchhammer, Soren}, institution = {Department of Mathematics, Saarland University, Saarbrücken}, journal = {Pattern Recognition}, number = 9, privnote = {uid:1320}, title = {Edge-based compression of cartoon-like images with homogeneous diffusion}, volume = 44, year = 2011 }
3. Volz, S., Bruhn, A., Valgaerts, L., & Zimmer, H. (2011). Modeling temporal coherence for optical flow. In I. C. S. Press (Hrsg.), Proceedings of IEEE International Conference on Computer Vision (ICCV 2011) (Bd. 2011). IEEE Computer Society Press.
  - BibTeX
  BibTeX
  @inproceedings{33b90d9840654fde8585a57b20e27512, author = {Volz, Sebastian and Bruhn, Andrés and Valgaerts, Levi and Zimmer, Henning}, booktitle = {Proceedings of IEEE International Conference on Computer Vision (ICCV 2011)}, editor = {Press, IEEE Computer Society}, privnote = {uid:1313}, publisher = {IEEE Computer Society Press}, title = {Modeling temporal coherence for optical flow}, volume = 2011, year = 2011 }
4. Faubel, F., Georges, M., Kumatani, K., Bruhn, A., & Klakow, D. (2011). Improving hands-free speech recognition in a car through audio-visual voice activity detection. Proceedings of Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2011).
  - BibTeX
  BibTeX
  @inproceedings{7e70fb368ee7408c9c21d52464a902b7, author = {Faubel, Friedrich and Georges, Munir and Kumatani, Kenichi and Bruhn, Andrés and Klakow, Dietrich}, booktitle = {Proceedings of Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2011)}, privnote = {uid:1382}, publisher = {IEEE Xplore}, title = {Improving hands-free speech recognition in a car through audio-visual voice activity detection}, year = 2011 }
5. Zimmer, H., Bruhn, A., & Weickert, J. (2011). Optic flow in harmony. International Journal of Computer Vision, 93(3), Article 3.
  - BibTeX
  BibTeX
  @article{377e7b9c9c4541628e3f57b352d489d9, author = {Zimmer, Henning and Bruhn, Andrés and Weickert, Joachim}, journal = {International Journal of Computer Vision}, number = 3, privnote = {uid:1321}, title = {Optic flow in harmony}, volume = 93, year = 2011 }
6. Zimmer, H., Bruhn, A., & Weickert, J. (2011). Freehand HDR Imaging of Moving Scenes with Simultaneous Resolution Enhancement. Computer Graphics Forum (Proceedings of EUROGRAPHICS), 30(2), Article 2.
  - BibTeX
  BibTeX
  @article{c80073cbd8eb468f9058b9d6c8a44c7d, author = {Zimmer, Henning and Bruhn, Andrés and Weickert, Joachim}, journal = {Computer Graphics Forum (Proceedings of EUROGRAPHICS)}, number = 2, privnote = {uid:1322}, title = {Freehand HDR Imaging of Moving Scenes with Simultaneous Resolution Enhancement}, volume = 30, year = 2011 }
2010
1. Gwosdek, P., Zimmer, H., Grewenig, S., Weickert, J., & Bruhn, A. (2010). A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework. In K. Kutulakos (Hrsg.), Proceedings of ECCV Workshop on Computer Vision with GPUs (CVGPU 2010). Springer.
  - BibTeX
  BibTeX
  @inproceedings{ac23ba0ca42741bb83d510f33a3815cd, author = {Gwosdek, Pascal and Zimmer, Henning and Grewenig, Sven and Weickert, Joachim and Bruhn, Andrés}, booktitle = {Proceedings of ECCV Workshop on Computer Vision with GPUs (CVGPU 2010).}, editor = {Kutulakos, K.}, privnote = {uid:1333}, publisher = {Springer}, title = {A highly efficient GPU implementation for variational optic flow based on the Euler-Lagrange framework}, year = 2010 }
2. Valgaerts, L., Bruhn, A., Zimmer, H., Weickert, J., Stoll, C., & Theobalt, C. (2010). Joint estimation of motion, structure and geometry from stereo sequences. In K. Danilidis, P. Maragos, & N. Paragios (Hrsg.), Proceedings of European Conference on Computer Vision (ECCV 2010). Lecture Notes in Computer Science (Bd. 6314). Springer.
  - BibTeX
  BibTeX
  @inproceedings{a57e77db15e646f887efac4cb25d353d, author = {Valgaerts, Levi and Bruhn, Andrés and Zimmer, Henning and Weickert, Joachim and Stoll, Christian and Theobalt, Christian}, booktitle = {Proceedings of European Conference on Computer Vision (ECCV 2010). Lecture Notes in Computer Science}, editor = {Danilidis, K. and Maragos, P. and Paragios, N.}, privnote = {uid:1332}, publisher = {Springer}, title = {Joint estimation of motion, structure and geometry from stereo sequences}, volume = 6314, year = 2010 }
3. Hauger, C., Weigand, H., Weickert, J., & Bruhn, A. (2010). Medizinisch optisches Beobachtungsgerät und Verfahren zum Erstellen einer stereoskopischen Zwischenperspektive in einem derartigen Gerät. Patent DE 10 20008 024 732 B4 2010.04.01, 2010.
  - BibTeX
  BibTeX
  @article{8541fec60ff345faaf6cacc7d66518a2, author = {Hauger, C. and Weigand, H. and Weickert, Joachim and Bruhn, Andrés}, journal = {Patent DE 10 20008 024 732 B4 2010.04.01}, privnote = {uid:1334}, title = {Medizinisch optisches Beobachtungsgerät und Verfahren zum Erstellen einer stereoskopischen Zwischenperspektive in einem derartigen Gerät}, volume = 2010, year = 2010 }
4. Schmaltz, C., Gwosdek, P., Bruhn, A., & Weickert, J. (2010). Electrostatic halftoning. Computer Graphics Forum, 29(8), Article 8.
  - BibTeX
  BibTeX
  @article{9efcefd069bf49d5824a040656970f01, author = {Schmaltz, Christian and Gwosdek, Pascal and Bruhn, Andrés and Weickert, Joachim}, journal = {Computer Graphics Forum}, number = 8, privnote = {uid:1323}, title = {Electrostatic halftoning}, volume = 29, year = 2010 }
5. Gwosdek, P., Weickert, J., & Bruhn, A. (2010). Variational optic flow on the Sony PlayStation 3. Journal of Real-Time Image Processing, 5(3), Article 3.
  - BibTeX
  BibTeX
  @article{73d12de1bb824dd6977b2a7336738a91, author = {Gwosdek, Pascal and Weickert, Joachim and Bruhn, Andrés}, journal = {Journal of Real-Time Image Processing}, number = 3, privnote = {uid:1327}, title = {Variational optic flow on the Sony PlayStation 3}, volume = 5, year = 2010 }
6. Grewenig, S., Weickert, J., & Bruhn, A. (2010). From box filtering to fast explicit diffusion. Awarded the DAGM 2010 Main Prize (Best Paper Award). In M. Goesele, S. Roth, A. Kujper, B. Schiele, & K. Schindler (Hrsg.), Proceedings of German Pattern Recognition Symposium (DAGM 2010). Lecture Notes in Computer Science (Bd. 6376). Springer.
  - BibTeX
  BibTeX
  @inproceedings{fa7c9b91e4374f50973d8cb805310d42, author = {Grewenig, Sven and Weickert, Joachim and Bruhn, Andrés}, booktitle = {Proceedings of German Pattern Recognition Symposium (DAGM 2010). Lecture Notes in Computer Science}, editor = {Goesele, M. and Roth, S. and Kujper, A. and Schiele, B. and Schindler, K.}, privnote = {uid:1329}, publisher = {Springer}, title = {From box filtering to fast explicit diffusion. Awarded the DAGM 2010 Main Prize (Best Paper Award)}, volume = 6376, year = 2010 }
2009
1. Zimmer, H., Bruhn, A., Weickert, J., Valgaerts, L., Salgado, A., Rosenhahn, B., & Seidel, H.-P. (2009). Complementary optic flow. In D. Cremers, Y. Boykov, A. Blake, & F. R. Schmidt (Hrsg.), Proceedings of International Conference on Energy Minimizing Methods in Computer Vision and Pattern Recognition (EMMCVPR 2009). Lecture Notes in Computer Science (Bd. 5681). Springer.
  - BibTeX
  BibTeX
  @inproceedings{a85f22ca23754ab3a37187920369072c, author = {Zimmer, Henning and Bruhn, Andrés and Weickert, Joachim and Valgaerts, Levi and Salgado, Agustin and Rosenhahn, Bodo and Seidel, Hans-Peter}, booktitle = {Proceedings of International Conference on Energy Minimizing Methods in Computer Vision and Pattern Recognition (EMMCVPR 2009). Lecture Notes in Computer Science}, editor = {Cremers, D. and Boykov, Y. and Blake, A. and Schmidt, F.R.}, privnote = {uid:1335}, publisher = {Springer}, title = {Complementary optic flow}, volume = 5681, year = 2009 }
2. Schmaltz, C., Weickert, J., & Bruhn, A. (2009). Beating the quality of JPEG 200 with anisotropic diffusion. In J. Denzler, G. Notni, & H. Süße (Hrsg.), Proceedings of German Pattern Recognition Symposium (DAGM 2009). Lecture Notes in Computer Science (Bd. 5748). Springer.
  - BibTeX
  BibTeX
  @inproceedings{3cd8a9267a4b4c05aa2bd563dc3ccc15, author = {Schmaltz, Christian and Weickert, Joachim and Bruhn, Andrés}, booktitle = {Proceedings of German Pattern Recognition Symposium (DAGM 2009). Lecture Notes in Computer Science}, editor = {Denzler, J. and Notni, G. and Süße, H.}, privnote = {uid:1336}, publisher = {Springer}, title = {Beating the quality of JPEG 200 with anisotropic diffusion}, volume = 5748, year = 2009 }
3. Ghodstinat, M., Bruhn, A., & Weickert, J. (2009). Deinterlacing with motion-compensated anisotropic diffusion. In D. Cremers, B. Rosenhahn, A. Yuille, & F. Schmidt (Hrsg.), Statistical and Geometrical Approaches to Visual Motion Analysis. Lecture Notes in Computer Science (5604. Aufl.). Springer.
  - BibTeX
  BibTeX
  @inbook{77dec2dbb27543dfaa03ff4110bd305b, author = {Ghodstinat, M. and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Statistical and Geometrical Approaches to Visual Motion Analysis. Lecture Notes in Computer Science}, edition = 5604, editor = {Cremers, D. and Rosenhahn, B. and Yuille, A. and Schmidt, F.}, privnote = {uid:1337}, publisher = {Springer}, title = {Deinterlacing with motion-compensated anisotropic diffusion}, year = 2009 }
2008
1. Bruhn, A. (2008). Bewegungsschätzung in Echtzeit mit Optimierungsansätzen. it - Information Technology, 50(1), Article 1.
  - BibTeX
  BibTeX
  @article{1d78d05a05fd411ea23443adc3d7bb2d, author = {Bruhn, Andrés}, journal = {it - Information Technology}, number = 1, privnote = {uid:1343}, publisher = {Oldenbourg Wissenschaftsverlag}, title = {Bewegungsschätzung in Echtzeit mit Optimierungsansätzen}, volume = 50, year = 2008 }
2. Valgaerts, L., Bruhn, A., & Weickert, J. (2008). A variational model for the joint recovery of the optical flow and the fundamental matrix. In G. Rigoll (Hrsg.), Proceedings of German Pattern Recognition Symposium (DAGM 2008). Lecture Notes in Computer Science (Bd. 5096). Springer.
  - BibTeX
  BibTeX
  @inproceedings{c85165dcf36e44e8a70cc084badeb28e, author = {Valgaerts, Levi and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of German Pattern Recognition Symposium (DAGM 2008). Lecture Notes in Computer Science}, editor = {Rigoll, G.}, privnote = {uid:1341}, publisher = {Springer}, title = {A variational model for the joint recovery of the optical flow and the fundamental matrix}, volume = 5096, year = 2008 }
3. Zimmer, H., Bruhn, A., Valgaerts, L., Breuß, M., Weickert, J., Rosenhahn, B., & Seidel, H.-P. (2008). PDE-based anisotropic disparity-driven stereo vision. In O. Deussen, D. Keim, & D. Saupe (Hrsg.), Proceedings of International Workshop on Vision, Modelling, and Visualization (VMV 2008) (Bd. 2008). AKA Heidelberg.
  - BibTeX
  BibTeX
  @inproceedings{53bc20d83f8f4c3a815a2aa1df45af16, author = {Zimmer, Henning and Bruhn, Andrés and Valgaerts, Levi and Breuß, Michael and Weickert, Joachim and Rosenhahn, Bodo and Seidel, Hans-Peter}, booktitle = {Proceedings of International Workshop on Vision, Modelling, and Visualization (VMV 2008)}, editor = {Deussen, O. and Keim, D. and Saupe, D.}, privnote = {uid:1338}, publisher = {AKA Heidelberg}, title = {PDE-based anisotropic disparity-driven stereo vision}, volume = 2008, year = 2008 }
4. Mainberger, M., Weickert, J., & Bruhn, A. (2008). Is dense optical flow useful to compute the fundamental matrix? Update with errata. In A. Campilho & M. Kamel (Hrsg.), Proceedings of International Conference on Image Analysis and Recognition (ICIAR 2008). Lecture Notes in Computer Science (Bd. 5112). Springer.
  - BibTeX
  BibTeX
  @inproceedings{39795a3adc9a4d3fb034f7411691cb52, author = {Mainberger, Markus and Weickert, Joachim and Bruhn, Andrés}, booktitle = {Proceedings of International Conference on Image Analysis and Recognition (ICIAR 2008). Lecture Notes in Computer Science}, editor = {Campilho, A. and Kamel, M.}, privnote = {uid:1342}, publisher = {Springer}, title = {Is dense optical flow useful to compute the fundamental matrix? Update with errata.}, volume = 5112, year = 2008 }
5. Gwosdek, P., Bruhn, A., & Weickert, J. (2008). High performance parallel optical flow algorithms on the Sony Playstation 3. In O. Deussen, D. Keim, & D. Saupe (Hrsg.), Proceedings of International Workshop on Vision, Modeling, and Visualization (VMV 2008) (Bd. 2008). AKA.
  - BibTeX
  BibTeX
  @inproceedings{3a3ac8d2426446469561d525283da9cf, author = {Gwosdek, Pascal and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of International Workshop on Vision, Modeling, and Visualization (VMV 2008)}, editor = {Deussen, O. and Keim, D. and Saupe, D.}, privnote = {uid:1339}, publisher = {AKA}, title = {High performance parallel optical flow algorithms on the Sony Playstation 3}, volume = 2008, year = 2008 }
6. Galic, I., Weickert, J., Welk, M., Bruhn, A., Belyaev, A., & Seidel, H.-P. (2008). Image compression with anisotropic diffusion. Journal of Mathematical Imaging and Vision, 31.
  - BibTeX
  BibTeX
  @article{96759b1426fa4d05a6358426e7c3daa9, author = {Galic, Irena and Weickert, Joachim and Welk, Martin and Bruhn, Andrés and Belyaev, A. and Seidel, Hans-Peter}, journal = {Journal of Mathematical Imaging and Vision}, privnote = {uid:1340}, title = {Image compression with anisotropic diffusion}, volume = 31, year = 2008 }
2007
1. Burgeth, B., Bruhn, A., Didas, S., Weickert, J., & Welk, M. (2007). Morphology for tensor data: Ordering versus PDE-based approach. Image and Vision Computing, 25(4), Article 4.
  - BibTeX
  BibTeX
  @article{6b73e41be7574cf0a580f0d9881bbddb, author = {Burgeth, Bernhard and Bruhn, Andrés and Didas, Stephan and Weickert, Joachim and Welk, Martin}, institution = {Saarland University, Saarbrücken}, journal = {Image and Vision Computing}, number = 4, privnote = {uid:1353}, title = {Morphology for tensor data: Ordering versus PDE-based approach}, volume = 25, year = 2007 }
2. Vogel, O., Bruhn, A., Weickert, J., & Didas, S. (2007). Direct shape-from-shading with adaptive higher order regularisation. In F. Sgallari, F. Murli, & N. Paragios (Hrsg.), Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2007). Lecture Notes in Computer Science (Bd. 4485). Springer.
  - BibTeX
  BibTeX
  @inproceedings{11933a29151448f6817d23abc86bf4e4, author = {Vogel, Oliver and Bruhn, Andrés and Weickert, Joachim and Didas, Stephan}, booktitle = {Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2007). Lecture Notes in Computer Science}, editor = {Sgallari, F. and Murli, F. and Paragios, N.}, privnote = {uid:1352}, publisher = {Springer}, title = {Direct shape-from-shading with adaptive higher order regularisation}, volume = 4485, year = 2007 }
3. Bruhn, A. (2007). Variationsansätze zur Bewegungsschätzung: Präzise Modellierung und effiziente Numerik. In D. W. et al. (Hrsg.), Ausgezeichnete Informatikdissertationen 2006. GI-Edition Lecture Notes in Informatics (LNI). Gesellschaft für Informatik.
  - BibTeX
  BibTeX
  @inbook{e8f0c1f3f19f4d309312f992f1d5cf81, author = {Bruhn, Andrés}, booktitle = {Ausgezeichnete Informatikdissertationen 2006. GI-Edition Lecture Notes in Informatics (LNI)}, editor = {et al., D. Wagner}, privnote = {uid:1349}, publisher = {Gesellschaft für Informatik}, title = {Variationsansätze zur Bewegungsschätzung: Präzise Modellierung und effiziente Numerik}, year = 2007 }
4. Burgeth, B., Papenberg, N., Bruhn, A., Welk, M., & Weickert, J. (2007). Mathematical morphology for matrix fields induced by the Loewner ordering in higher dimensions. Signal Processing, 87(2), Article 2.
  - BibTeX
  BibTeX
  @article{0174474dfcc5447abfe3c0226d723ffe, author = {Burgeth, Bernhard and Papenberg, Nils and Bruhn, Andrés and Welk, Martin and Weickert, Joachim}, institution = {Dept. of Mathematics, Saarland University, Saarbrücken}, journal = {Signal Processing}, number = 2, privnote = {uid:1354}, title = {Mathematical morphology for matrix fields induced by the Loewner ordering in higher dimensions}, volume = 87, year = 2007 }
5. Demetz, O., Weickert, J., Welk, M., & Bruhn, A. (2007). Beauty with variational methods: An optic flow approach to hairstyle simulation. In f. Sgallari, A. Murli, & N. Paragios (Hrsg.), Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2007). Lecture Notes in Computer Science (Bd. 4485). Springer.
  - BibTeX
  BibTeX
  @inproceedings{5c0d8286480e4fa38aca2bead483e333, author = {Demetz, Oliver and Weickert, Joachim and Welk, Martin and Bruhn, Andrés}, booktitle = {Proceedings of International Conference on Scale Space and Variational Methods in Computer Vision (SSVM 2007). Lecture Notes in Computer Science}, editor = {f. Sgallari and Murli, A. and Paragios, N.}, privnote = {uid:1351}, publisher = {Springer}, title = {Beauty with variational methods: An optic flow approach to hairstyle simulation}, volume = 4485, year = 2007 }
6. Mileva, Y., Bruhn, A., & Weickert, J. (2007). Illumination-robust variational optical flow with photometric invariants. In F. A. Hamprecht, C. Schnörr, & B. Jähne (Hrsg.), Proceedings of German Pattern Recognition Symposium (DAGM 2007). Lecture Notes in Computer Science (Bd. 4713). Springer.
  - BibTeX
  BibTeX
  @inproceedings{9a228bd52d98445a97971abbbd47ffc6, author = {Mileva, Yana and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of German Pattern Recognition Symposium (DAGM 2007). Lecture Notes in Computer Science}, editor = {Hamprecht, F.A. and Schnörr, C. and Jähne, B.}, privnote = {uid:1348}, publisher = {Springer}, title = {Illumination-robust variational optical flow with photometric invariants}, volume = 4713, year = 2007 }
7. Slesareva, N., Bühler, T., Hagenburg, K., Weickert, J., Bruhn, A., Karni, Z., & Seidel, H.-P. (2007). Robust variational reconstruction from multiple views. In B. K. Esboll & K. S. Pedersen (Hrsg.), Proceedings of Scandinavian Conference on Image Analysis (SCIA 2007). Lecture Notes in Computer Science (Bd. 4522). Springer.
  - BibTeX
  BibTeX
  @inproceedings{746af4fc08ec400f89fb71ba2ae1522b, author = {Slesareva, Natalia and Bühler, T. and Hagenburg, Kai and Weickert, Joachim and Bruhn, Andrés and Karni, Zachi and Seidel, Hans-Peter}, booktitle = {Proceedings of Scandinavian Conference on Image Analysis (SCIA 2007). Lecture Notes in Computer Science}, editor = {Esboll, B.K. and Pedersen, K.S.}, privnote = {uid:1350}, publisher = {Springer}, title = {Robust variational reconstruction from multiple views}, volume = 4522, year = 2007 }
2006
1. Papenberg, N., Bruhn, A., Brox, T., Didas, S., & Weickert, J. (2006). Highly accurate optic flow computation with theoretically justified warping. International Journal of Computer Vision, 67(2), Article 2.
  - BibTeX
  BibTeX
  @article{6b3da3d16fed47a491eb5e5bdb608e0f, author = {Papenberg, Nils and Bruhn, Andrés and Brox, Thomas and Didas, Stephan and Weickert, Joachim}, institution = {Department of Mathematics, Saarland University, Saarbrücken}, journal = {International Journal of Computer Vision}, number = 2, privnote = {uid:1357}, title = {Highly accurate optic flow computation with theoretically justified warping}, volume = 67, year = 2006 }
2. Weickert, J., Bruhn, A., Brox, T., & Papenberg, N. (2006). A survey on variational optic flow methods for small displacements. In O. Scherzer (Hrsg.), Mathematical models for registration and applications to medical imaging. Springer.
  - BibTeX
  BibTeX
  @inbook{9e25c5537ebd45ca87220308a09e851e, author = {Weickert, Joachim and Bruhn, Andrés and Brox, Thomas and Papenberg, Nils}, booktitle = {Mathematical models for registration and applications to medical imaging}, editor = {Scherzer, O.}, institution = {Dept. of Mathematics, Saarland University, Saarbrücken}, privnote = {uid:1356}, publisher = {Springer}, title = {A survey on variational optic flow methods for small displacements}, year = 2006 }
3. Brox, T., Bruhn, A., & Weickert, J. (2006). Variational motion segmentation with level sets. In H. Bischof, A. Leonardis, & A. Pinz (Hrsg.), Proceedings of European Conference on Computer Vision (ECCV 2006). Lecture Notes in Computer Science (Bd. 3951). Springer.
  - BibTeX
  BibTeX
  @inproceedings{d666061f89d74a4eb70fd813098f0580, author = {Brox, Thomas and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of European Conference on Computer Vision (ECCV 2006). Lecture Notes in Computer Science}, editor = {Bischof, H. and Leonardis, A. and Pinz, A.}, privnote = {uid:1358}, publisher = {Springer}, title = {Variational motion segmentation with level sets}, volume = 3951, year = 2006 }
4. Mrázek, P., Weickert, J., & Bruhn, A. (2006). On robust estimation and smoothing with spatial and tonal kernels. In R. Klette, R. Kozera, L. Noakes, & J. Weickert (Hrsg.), Geometric Properties from Incomplete Data. Springer.
  - BibTeX
  BibTeX
  @inbook{08e83e02eb5943ebb5f119448449ab32, author = {Mrázek, Pavel and Weickert, Joachim and Bruhn, Andrés}, booktitle = {Geometric Properties from Incomplete Data}, editor = {Klette, R. and Kozera, R. and Noakes, L. and Weickert, J.}, institution = {DFG Priority Programme 1114, University of Bremen}, privnote = {uid:1360}, publisher = {Springer}, title = {On robust estimation and smoothing with spatial and tonal kernels}, year = 2006 }
5. Bruhn, A. (2006). Variational Optic Flow Computation: Accurate Modelling and Efficient Numerics. Awarded the 2006 Outstanding Dissertation Award by the German Computer Society(GI). Awarded the 2006 Dr. Eduard Martin Prize by the Saarland University. Department of Mathematics and Computer Science, Saarland University.
  - BibTeX
  BibTeX
  @phdthesis{80e0d60c6bab4297a12358c900f59820, author = {Bruhn, Andrés}, privnote = {uid:1383}, school = {Department of Mathematics and Computer Science, Saarland University}, title = {Variational Optic Flow Computation: Accurate Modelling and Efficient Numerics. Awarded the 2006 Outstanding Dissertation Award by the German Computer Society(GI). Awarded the 2006 Dr. Eduard Martin Prize by the Saarland University}, year = 2006 }
6. Bruhn, A., & Weickert, J. (2006). A confidence measure for variational optic flow methods. In R. Klette, R. Kozera, L. Noakes, & J. Weickert (Hrsg.), Geometric Properties from Incomplete Data. Springer.
  - BibTeX
  BibTeX
  @inbook{a0011e6824934d6eb19b06fad3357345, author = {Bruhn, Andrés and Weickert, Joachim}, booktitle = {Geometric Properties from Incomplete Data}, editor = {Klette, R. and Kozera, R. and Noakes, L. and Weickert, J.}, institution = {Dept. of Mathematics, Saarland University, Saarbrücken}, privnote = {uid:1359}, publisher = {Springer}, title = {A confidence measure for variational optic flow methods}, year = 2006 }
7. Bruhn, A., Weickert, J., Kohlberger, T., & Schnörr, C. (2006). A multigrid platform for real-time motion computation with discontinuity-preserving variational methods. International Journal of Computer Vision, 70(3), Article 3.
  - BibTeX
  BibTeX
  @article{c40b614723de4b3fbfd8a52f5f0ccf1e, author = {Bruhn, Andrés and Weickert, Joachim and Kohlberger, Timo and Schnörr, Christoph}, journal = {International Journal of Computer Vision}, number = 3, privnote = {uid:1355}, title = {A multigrid platform for real-time motion computation with discontinuity-preserving variational methods}, volume = 70, year = 2006 }
2005
1. Kohlberger, T., Schnörr, C., Bruhn, A., & Weickert, J. (2005). Domain decomposition for variational optical flow computation. IEEE Transactions on Image Processing, 14(8), Article 8.
  - BibTeX
  BibTeX
  @article{47084226c7a944e99e9ddb9bc1e18b95, author = {Kohlberger, Timo and Schnörr, Christoph and Bruhn, Andrés and Weickert, Joachim}, journal = {IEEE Transactions on Image Processing}, number = 8, privnote = {uid:1362}, publisher = {IEEE Computer Society Press}, title = {Domain decomposition for variational optical flow computation}, volume = 14, year = 2005 }
2. Bruhn, A., Weickert, J., & Schnörr, C. (2005). Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. - Update with errata. International Journal of Computer Vision, 61(3), Article 3.
  - BibTeX
  BibTeX
  @article{799dd989500b4d938210d36153378e32, author = {Bruhn, Andrés and Weickert, Joachim and Schnörr, Christoph}, journal = {International Journal of Computer Vision}, number = 3, privnote = {uid:1369}, title = {Lucas/Kanade meets Horn/Schunck: Combining local and global optic flow methods. - Update with errata}, volume = 61, year = 2005 }
3. Galic, I., Weickert, J., Welk, M., Bruhn, A., Belyaev, A., & Seidel, H.-P. (2005). Towards PDE-based image compression. In N. Paragios, O. Faugeras, T. Chan, & C. Schnörr (Hrsg.), Proceedings of International Workshop on Variational, Geometric, and Level Set Methods in Computer Vision (VLSM 2005). Lecture Notes in Computer Science (Bd. 3752). Springer.
  - BibTeX
  BibTeX
  @inproceedings{cfbcffea4d2d45d8a24bfc3482414298, author = {Galic, Irena and Weickert, Joachim and Welk, Martin and Bruhn, Andrés and Belyaev, A. and Seidel, Hans-Peter}, booktitle = {Proceedings of International Workshop on Variational, Geometric, and Level Set Methods in Computer Vision (VLSM 2005). Lecture Notes in Computer Science}, editor = {Paragios, N. and Faugeras, O. and Chan, T. and Schnörr, C.}, privnote = {uid:1363}, publisher = {Springer}, title = {Towards PDE-based image compression}, volume = 3752, year = 2005 }
4. Kohlberger, T., Schnörr, C., Bruhn, A., & Weickert, J. (2005). Domain decomposition for nonlinear problems: a control-theoretic approach. University of Mannheim.
  - BibTeX
  BibTeX
  @techreport{9355801818ef4ea58c6cbb255a96b761, author = {Kohlberger, Timo and Schnörr, Christoph and Bruhn, Andrés and Weickert, Joachim}, institution = {University of Mannheim}, privnote = {uid:1365}, title = {Domain decomposition for nonlinear problems: a control-theoretic approach}, year = 2005 }
5. Burgeth, B., Papenberg, N., Bruhn, A., Welk, M., Feddern, C., & Weickert, J. (2005). Morphology for higher-dimensional tensor data via Loewner ordering. In C. Ronse, L. Najman, & E. Decencière (Hrsg.), Proceedings of International Symposium on Mathematical Morphology (ISMM 2005) (Bd. 30). Springer.
  - BibTeX
  BibTeX
  @inproceedings{e1f01baeeefd464aa2459de69553edde, author = {Burgeth, Bernhard and Papenberg, Nils and Bruhn, Andrés and Welk, Martin and Feddern, Christian and Weickert, Joachim}, booktitle = {Proceedings of International Symposium on Mathematical Morphology (ISMM 2005)}, editor = {Ronse, C. and Najman, L. and Decencière, E.}, privnote = {uid:1367}, publisher = {Springer}, title = {Morphology for higher-dimensional tensor data via Loewner ordering}, volume = 30, year = 2005 }
6. Slesareva, N., Bruhn, A., & Weickert, J. (2005). Optic flow goes stereo: A variational method for estimating discontinuity-preserving dense desparity maps. Awarded a DAGM 2005 Paper Prize. In W. Kropatsch, R. Sablatnig, & A. Hanbury (Hrsg.), Proceedings of German Pattern Recognition Symposium (DAGM 2005). Lecture Notes in Computer Science (Bd. 3663). Springer.
  - BibTeX
  BibTeX
  @inproceedings{9624fdd66afe42138e17c360817ecb79, author = {Slesareva, Natalia and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of German Pattern Recognition Symposium (DAGM 2005). Lecture Notes in Computer Science}, editor = {Kropatsch, W. and Sablatnig, R. and Hanbury, A.}, privnote = {uid:1361}, publisher = {Springer}, title = {Optic flow goes stereo: A variational method for estimating discontinuity-preserving dense desparity maps. Awarded a DAGM 2005 Paper Prize}, volume = 3663, year = 2005 }
7. Bruhn, A., Weickert, J., Kohlberger, T., & Schnörr, C. (2005). Discontinuity-preserving computation of variational optic flow in real-time. In R. Kimmel, N. Sochen, & J. Weickert (Hrsg.), Proceedings of International Conference on Scale-Space and PDE Methods in Computer Vision (Scale Space 2005). Lecture Notes in Computer Science (Bd. 3459). Springer.
  - BibTeX
  BibTeX
  @inproceedings{22bf59c2e5594c6a9c70138c1941ecaf, author = {Bruhn, Andrés and Weickert, Joachim and Kohlberger, Timo and Schnörr, Christoph}, booktitle = {Proceedings of International Conference on Scale-Space and PDE Methods in Computer Vision (Scale Space 2005). Lecture Notes in Computer Science}, editor = {Kimmel, R. and Sochen, N. and Weickert, J.}, privnote = {uid:1368}, publisher = {Springer}, title = {Discontinuity-preserving computation of variational optic flow in real-time}, volume = 3459, year = 2005 }
8. Bruhn, A., Weickert, J., Feddern, C., Kohlberger, T., & Schnörr, C. (2005). Variational optic flow computation in real-time. IEEE Transactions on Image Processing, 14(5), Article 5.
  - BibTeX
  BibTeX
  @article{9326b21b5141451d81b0fe0e8869c69f, author = {Bruhn, Andrés and Weickert, Joachim and Feddern, Christian and Kohlberger, Timo and Schnörr, Christoph}, institution = {Dept. of Mathematics, Saarland University, Saarbrücken}, journal = {IEEE Transactions on Image Processing }, number = 5, privnote = {uid:1366}, publisher = {IEEE Computer Society Press}, title = {Variational optic flow computation in real-time}, volume = 14, year = 2005 }
9. Bruhn, A., & Weickert, J. (2005). Towards ultimate motion estimation: Combining highest accuracy with real-time performance. Proceedings of IEEE International Conference on Computer Vision (ICCV 2005), 1.
  - BibTeX
  BibTeX
  @inproceedings{272ede53fe4e4863aa8b2c5ea188d3de, author = {Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of IEEE International Conference on Computer Vision (ICCV 2005)}, privnote = {uid:1364}, publisher = {IEEE Computer Society Press}, title = {Towards ultimate motion estimation: Combining highest accuracy with real-time performance}, volume = 1, year = 2005 }
2004
1. Bruhn, A., Jakob, T., Fischer, M., Kohlberger, T., Weickert, J., Brüning, U., & Schnörr, C. (2004). High performance cluster computing with 3-D nonlinear diffusion filters. Real-Time Imaging, 10(1), Article 1.
  - BibTeX
  BibTeX
  @article{4720202348984b66b9577fa9286cfad7, author = {Bruhn, Andrés and Jakob, Tobias and Fischer, Markus and Kohlberger, Timo and Weickert, Joachim and Brüning, Ulrich and Schnörr, Christoph}, institution = {Dept. of Mathematics, Saarland University, Saarbrücken}, journal = {Real-Time Imaging}, number = 1, privnote = {uid:1372}, title = {High performance cluster computing with 3-D nonlinear diffusion filters}, volume = 10, year = 2004 }
2. Weickert, J., Bruhn, A., Papenberg, N., & Brox, T. (2004). Variational optic llow computation : From continuous models to algorithms. Proceedings of International Workshop on Computer Vision and Image Analysis (IWCVIA 2003), 26.
  - BibTeX
  BibTeX
  @article{5b1ae92d30844b438cf8d6bfaf9bf625, author = {Weickert, Joachim and Bruhn, Andrés and Papenberg, Nils and Brox, Thomas}, editor = {Alvarez, L.}, institution = {University of Las Palmas de Gran Canaria}, journal = {Proceedings of International Workshop on Computer Vision and Image Analysis (IWCVIA 2003)}, privnote = {uid:1374}, title = {Variational optic llow computation : From continuous models to algorithms}, volume = 26, year = 2004 }
3. Brox, T., Bruhn, A., Papenberg, N., & Weickert, J. (2004). High accuracy optical flow estimation based on a theory for warping. Awarded the ECCV 2004 Longuet-Higgins-Prize (Best Paper Award). In T. Pajdla & J. Matas (Hrsg.), Proceedings of European Conference on Computer Vision (ECCV 2004). Lecture Notes in Computer Science (Bd. 3024). Springer.
  - BibTeX
  BibTeX
  @inproceedings{012cad23d8f44d25b3a9d3e5a6b3031e, author = {Brox, Thomas and Bruhn, Andrés and Papenberg, Nils and Weickert, Joachim}, booktitle = {Proceedings of European Conference on Computer Vision (ECCV 2004). Lecture Notes in Computer Science}, editor = {Pajdla, T. and Matas, J.}, privnote = {uid:1370}, publisher = {Springer}, title = {High accuracy optical flow estimation based on a theory for warping. Awarded the ECCV 2004 Longuet-Higgins-Prize (Best Paper Award)}, volume = 3024, year = 2004 }
4. Kohlberger, T., Schnörr, C., Bruhn, A., & Weickert, J. (2004). Parallel variational motion estimation by domain decomposition and cluster computing. In T. Pajdla & J. Matas (Hrsg.), Proceedings of European Conference on Computer Vision (ECCV 2004). Lecture Notes in Computer Science (Bd. 3024). Springer.
  - BibTeX
  BibTeX
  @inproceedings{d92f239512fb4fff96f97a841350a77b, author = {Kohlberger, Timo and Schnörr, Christoph and Bruhn, Andrés and Weickert, Joachim}, booktitle = {Proceedings of European Conference on Computer Vision (ECCV 2004). Lecture Notes in Computer Science}, editor = {Pajdla, T. and Matas, J.}, privnote = {uid:1371}, publisher = {Springer}, title = {Parallel variational motion estimation by domain decomposition and cluster computing}, volume = 3024, year = 2004 }
5. Papenberg, N., Bruhn, A., Brox, T., & Weickert, J. (2004). Numerical justification for multiresolution optical flow computation. In L. Alvarez (Hrsg.), Proceedings of International Workshop on Computer Vision and Image Analysis (IWCVIA 2003) (Bd. 26).
  - BibTeX
  BibTeX
  @inproceedings{ca6e9f39e66e4d4b9421aa95e0405615, author = {Papenberg, Nils and Bruhn, Andrés and Brox, Thomas and Weickert, Joachim}, booktitle = {Proceedings of International Workshop on Computer Vision and Image Analysis (IWCVIA 2003)}, editor = {Alvarez, L.}, institution = {University of Las Palmas de Gran Canaria}, privnote = {uid:1373}, title = {Numerical justification for multiresolution optical flow computation}, volume = 26, year = 2004 }
2003
1. Kohlberger, T., Schnörr, C., Weickert, J., & Bruhn, A. (2003). Domain decomposition for parallel veriational optic flow computation. In B. Michaelis & G. Krell (Hrsg.), Proceedings of German Pattern Recognition Symposium (DAGM 2003). Lecture Notes in Computer Science (Bd. 2781). Springer.
  - BibTeX
  BibTeX
  @inproceedings{3a0120de93ff4aef87c47464d27fa9e5, author = {Kohlberger, Timo and Schnörr, Christoph and Weickert, Joachim and Bruhn, Andrés}, booktitle = {Proceedings of German Pattern Recognition Symposium (DAGM 2003). Lecture Notes in Computer Science}, editor = {Michaelis, B. and Krell, G.}, privnote = {uid:1376}, publisher = {Springer}, title = {Domain decomposition for parallel veriational optic flow computation}, volume = 2781, year = 2003 }
2. Slogsnat, D., Fischer, M., Bruhn, A., Weickert, J., & Brüning, U. (2003). Low level parallelization of nonlinear diffusion filtering algorithms for cluster computing environments. In H. Kosch, L. Böszörményi, & H. Hellwagner (Hrsg.), Proceedings of European Conference on Parallel and Distributed Computing (Euro-Par 2003). Lecture Notes in Computer Science (Bd. 2790). Springer.
  - BibTeX
  BibTeX
  @inproceedings{25f6f9e3dc01409595fe11d87c10217b, author = {Slogsnat, David and Fischer, Markus and Bruhn, Andrés and Weickert, Joachim and Brüning, Ulrich}, booktitle = {Proceedings of European Conference on Parallel and Distributed Computing (Euro-Par 2003). Lecture Notes in Computer Science}, editor = {Kosch, H. and Böszörményi, L. and Hellwagner, H.}, privnote = {uid:1375}, publisher = {Springer}, title = {Low level parallelization of nonlinear diffusion filtering algorithms for cluster computing environments}, volume = 2790, year = 2003 }

Fachgebiet

Computer Vision

Motion Estimation
3-D Stereo Reconstruction
Image Registration
Shape-from-Shading

Scientific Computing

Variational Methods
Multigrid Methods
Machine Learning
Efficient Numerics

Image Processing

Image Denoising
Dithering
Image and Video Compression
Deinterlacing

Fields of Applications

Software/Movie Industry
Driver Assistance Systems
Pharmaceutical Technology
Material Sciences

Lehrangebote von VIS
Lehrangebote am VIS in C@MPUS

In der Lehre trägt die Abteilung zusammen mit den anderen Abteilungen des Instituts zur Ausbildung in den Bachelor- und Master-Programmen der Informatik in Bildverarbeitung, Computer Vision, Mustererkennung und Künstlicher Intelligenz bei.

Kurzbiographie

Andrés Bruhn is a professor of computer science at the University of Stuttgart where he heads the Intelligent Systems group at the Institute for Visualization and Interactive Systems (VIS). He received a diploma degree in Computer Engineering from the University of Mannheim, Mannheim, Germany (2001) and a Ph.D. degree in Computer Science from Saarland University, Saarbrücken, Germany (2006). After working as a postdoctoral researcher (2006-2007) he was associated as an assistant professor with the Mathematical Image Analysis Group at Saarland University, Saarbrücken, Germany (2007-2012). During this time he spent two months as a visiting reasearcher at the University of Las Palmas, Gran Canaria, Spain (2009) and built up an independent research group on Vision and Image Processing within the Cluster of Excellence " Multimodal Computing and Interaction" (2010-2012). His research interests include various areas in the field of computer vision and image processing such as motion estimation, stereo reconstruction, image and video enhancement, data compression as well as the design of efficient numerical schemes for many of the aforementioned tasks. In these fields he published over 100 refereed papers with over 10000 citations and an h-index of 40. Prof. Bruhn serves on the programme committee of numereous conferences including ICCV, ECCV, and CVPR and regularly reviews for all major computer vision journals. His publications received several awards, among them the 2004 Longuet-Higgins Best Paper Award of the European Conference on Computer Vision (ECCV), the 2006 Olympus Prize (German Pattern Recognition Award) of the German Pattern Recognition Society (DAGM), the 2010 Best Paper Award of the German Conference on Pattern Recognition (GCPR) as well as the 2006 GI Outstanding Dissertation Award of the German Society of Computer Science (GI), the Swiss Computer Science Society (SI), the Austrian Computer Society (OCG) and the German Chapters of the ACM (GChACM). Moreover, he was nominated as one of two national finalists for the 2008 Cor Baayen Award of the European Research Consortium for Informatics and Mathematics (ERCIM). Recently, he was awarded the 2014 Koenderink Prize at the European Conference on Computer Vision (ECCV) for fundamental contributions in computer vision.

Preise

2022 - ECCV Robust Vision Challenge Award
           Winner of the Category "Optical Flow"
           (with A. Jahedi, M.Luz, M. Rivinius, and L.Mehl)
       awarded by the ECCV Robust Vision Challenge Workshop

2022 - ECCV AROW Best Paper Award
           (with J. Schmalfuss and L.Mehl)
       awarded by the ECCV Workshop on
          Adversarial Robustness in the Real World

2019 - University of Stuttgart Publication Award
(with D.Maurer, Y.C.Ju, and M.Breuß)
awarded by the University of Stuttgart

2018 - CVPR Robust Vision Challenge Runner-Up Award
           Second Place in the Category "Optical Flow"
           (with D.Maurer)
       awarded by the CVPR Robust Vision Challenge Workshop

2017 - EXPRESSIVE Best Paper Award
(with K.Kurzhals, M.Stoll, and D.Weiskopf)

2014 - Koenderink Prize
          for Fundamental Contributions in Computer Vision
          (with T.Brox, N.Papenberg, and J.Weickert)
          awarded by the European Conference on Computer Vision

2014 - ECCV Outstanding Reviewer Award
awarded by the European Conference on Computer Vision

2012 - DAGM-OAGM Paper Award
          (with C.Schroers, H.Zimmer, L.Valgaerts, O.Demetz and J.Weickert)
          awarded by the German Pattern Recognition Society
          and the Austrian Pattern Recognition Society

2011 - ICCV Outstanding Reviewer Award
awarded by the International Conference on Computer Vision

2010 - ACCV Outstanding Reviewer Award
awarded by the Asian Conference on Computer Vision

2010 - DAGM Main Prize (Best Paper Award)
(with S.Grewenig and J.Weickert)
awarded by the German Pattern Recognition Society

2008 - ECCV Outstanding Reviewer Award
awarded by the European Conference on Computer Vision

2008 - ERCIM Cor Baayen Award Finalist
nominated by the European Research Consortium for Informatics
and Mathematics

2008 - Excellence in Teaching Award
awarded by the Computer Science Student Council of Saarland University

2007 - Dr. Eduard Martin Prize
awarded by the Saarland University

2006 - GI Outstanding Dissertation Award
          awarded by the German Computer Science Society
          the Swiss Computer Science Society
          the Austrian Computer Society
          and the German Chapter of the ACM

2006 - Olympus Prize (German Pattern Recognition Award)
awarded by the German Pattern Recognition Society

2005 - DAGM Paper Award
(with N.Slesareva and J.Weickert)
awarded by the German Pattern Recognition Society

2004 - ECCV Longuet-Higgins Prize (Best Paper Award)
(with T.Brox, N.Papenberg, and J.Weickert)
awarded by the European Conference on Computer Vision

2002 - DAGM Paper Award
(with J.Weickert and C.Schnörr)
awarded by the German Pattern Recognition Society

Programm-Kommitees

2017 - German Conference on Pattern Recognition (GCPR, PC)

2017 - International Conference on Scale Space and Variational Methods
in Computer Vision (SSVM, PC)

2016 - British Machine Vision Conference (BMVC, PC + Session Chair)

2016 - German Conference on Pattern Recognition (GCPR, PC)

2015 - International Conference on Scale Space and Variational Methods
in Computer Vision (SSVM, PC)

2015 - German Conference on Pattern Recognition (GCPR, PC)

2015 - International Conference on Energy Minimization Methods in Computer Vision
and Pattern Recognition (EMMCVPR, PC)

2014 - European Conference on Computer Vision (ECCV, PC)
Awarded an Outstanding Reviewer Award

2014 - German Conference on Pattern Recognition (GCPR, PC)

2014 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR, PC)

2013 - International Workshop on Vision, Modeling and Visualization (VMV, PC)

2013 - German Conference on Pattern Recognition (GCPR, AC + Session Chair)

2013 - International Conference on Energy Minimization Methods in Computer Vision
and Pattern Recognition (EMMCVPR, PC)

2013 - International Conference on Scale Space and Variational Methods
in Computer Vision (SSVM, PC)

2012 - Asian Conference on Computer Vision (ACCV, PC + Session Chair)

2012 - German Conference on Pattern Recognition (DAGM, AC + Session Chair)

2012 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR, PC)

2011 - IEEE International Conference on Computer Vision (ICCV, PC)
Awarded an Outstanding Reviewer Award

2011 - International Conference on Energy Minimization Methods in Computer Vision
and Pattern Recognition (EMMCVPR, PC)

2011 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR, PC)

2010 - Asian Conference on Computer Vision (ACCV, PC)
Awarded an Outstanding Reviewer Award

2010 - European Conference on Computer Vision (ECCV, PC)

2010 - International Workshop on Vision, Modeling and Visualization (VMV, PC)

2010 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR, PC)

2010 - International Conference on Computer Vision Theory and Applications (VISAPP, PC)

2009 - International Workshop on Vision, Modeling and Visualization (VMV, PC)

2009 - International Conference on Energy Minimization Methods in Computer Vision
and Pattern Recognition (EMMCVPR, PC + Session Chair)

2009 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR, PC)

2009 - International Conference on Computer Vision Theory and Applications (VISAPP, PC)

2008 - European Conference on Computer Vision (ECCV, PC)
Awarded an Outstanding Reviewer Award

2008 - International Workshop on Vision, Modeling and Visualization (VMV, PC)

2008 - Tribute Workshop in Honour of Professor Peter Johansen

2007 - IEEE International Conference on Computer Vision (ICCV, PC)

2007 - International Workshop on Vision, Modeling and Visualization (VMV, PC)

2007 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR, RC)

2007 - Asian Conference on Computer Vision (ACCV, PC)

2006 - IEEE Conference on Computer Vision and Pattern Recognition (CVPR, PC)

2006 - European Conference on Computer Vision (ECCV, PC)

Reviewing

National Science Foundations

Chilean Science Foundation (FONDECYT)
German Research Foundation (DFG)
Israel Science Foundation (ISF)
Research Foundation Flanders (FWO)

Journals

Konferenzen

IEEE International Conference on Computer Vision (ICCV)
European Conference on Computer Vision (ECCV)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Asian Conference on Computer Vision (ACCV)
International Conference and Exhibition on Computer Graphics and Interactive Techniques (SIGGRAPH)
Conference of the European Association for Computer Graphics (EUROGRAPHICS)
Conf. and Exhibition on Computer Graphics and Interactive Techniques Asia (SIGGRAPH Asia)
Int. Conference on Scale Space and Variational Methods in Computer Vision (SSVM)
Int. Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR)
International Conference on Computer Analysis of Images and Patterns (CAIP)
International Conference on Computer Vision Theory and Applications (VISAPP)
IEEE Pacific-Rim Symposium on Image and Video Technology (PSIVT)
German Conference on Pattern Recognition (GCPR, DAGM)
Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA)
IEEE Workshop on Variational, Geometric and Level Set Methods in Computer Vision (VLSM)
International Workshop on Vision, Modelling and Visualization (VMV)

SFB TRR 161-Projekte

B04
Mehr zum SFB TRR 161

Andrés Bruhn

Kontakt

Sprechstunde

Publikationen

2024

BibTeX

Link

2023

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

2022

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

2021

BibTeX

Link

2020

BibTeX

Link

BibTeX

Link

BibTeX

Link

2019

BibTeX

Link

2018

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

2017

BibTeX

BibTeX

Link

BibTeX

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

2016

BibTeX

BibTeX

BibTeX

2015

BibTeX

Link

BibTeX

BibTeX

2014

BibTeX

Link

BibTeX

BibTeX

Link

2013

BibTeX