B04 | Adaptive Algorithms for Motion Estimation
This project aims at developing novel algorithms for optical flow (2D motion) and scene flow (3D motion) estimation. Instead of relying on fixed assumptions, the goal is to adaptively integrate prior knowledge and other available information in order to design approaches that are not only highly accurate but also generalize well across datasets.
Fig. 1: Optical flow estimation on the automotive KITTI dataset using the method of Maurer et al. (BMVC 2018).
Research Questions
How can we develop algorithms for adaptive motion estimation of high accuracy and generalizability that are applicable in the wild?
To which extent can concepts be generalized from the 2D to the 3D domain and how can additional constraints imposed by the 3D world improve the estimation?
How can we transfer the benefits of adaptive algorithms to specific applications?
Publications
- A. Jahedi, M. Rivinius, N. Berenguel Senn, and A. Bruhn, “Reviving Unsupervised Optical Flow: Concept Reevaluation, Multi-Scale Advances and Full Open-Source Release.” IEEE, pp. 1533–1542, Mar. 2026. doi: 10.1109/wacv61042.2026.00155.
- V. Oei et al., “RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo,” in 14th International Conference on Learning Representations (ICLR 2026), Apr. 2026.
- J. Schmid, A. Jahedi, N. Berenguel Senn, and A. Bruhn, “MS-RAFT-3D: A Multi-Scale Architecture for Recurrent Image-Based Scene Flow,” in IEEE International Conference on Image Processing (ICIP), Sep. 2025.
- E. Scheurer, J. Schmalfuß, A. Lis, and A. Bruhn, “Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow,” in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, 2024, pp. 6475–6484. doi: 10.1109/wacv57701.2024.00636.
- A. Jahedi, M. Luz, M. Rivinius, and A. Bruhn, “CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning,” in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, 2024, pp. 6885–6894. doi: 10.1109/wacv57701.2024.00675.
- L. Mehl, A. Bruhn, M. Gross, and C. Schroers, “Stereo Conversion with Disparity-Aware Warping, Compositing and Inpainting,” in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, 2024, pp. 4248–4257. doi: 10.1109/wacv57701.2024.00421.
- A. Jahedi, M. Luz, M. Rivinius, L. Mehl, and A. Bruhn, “MS-RAFT+: High Resolution Multi-Scale RAFT,” International Journal of Computer Vision, pp. 1573–1405, 2023, doi: 10.1007/s11263-023-01930-7.
- J. Schmalfuß, P. Scholze, and A. Bruhn, “A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow,” Proceedings of the European Conference on Computer Vision (ECCV), Oct. 2022, doi: 10.1007/978-3-031-20047-2_11.
- K. Kurzhals, M. Stoll, A. Bruhn, and D. Weiskopf, “FlowBrush: Optical Flow Art,” in Symposium on Computational Aesthetics, Sketch-Based Interfaces and Modeling, and Non-Photorealistic Animation and Rendering (EXPRESSIVE, co-located with SIGGRAPH)., 2017, pp. 1:1–1:9. doi: 10.1145/3092912.3092914.
Project Group A
Models and Measures
Completed
Project Group B
Adaptive Algorithms
Completed
Project Group C
Interaction
Completed
Project Group D
Applications
Completed
FOR SCIENTISTS
Projects
People
Publications
Graduate School
Equal Opportunity
FOR PUPILS
PRESS AND MEDIA
SOCIAL MEDIA
© SFB-TRR 161 | Quantitative Methods for Visual Computing | 2019.