PlayStation
RoCo-23 · SPEAR-L-K1
RbS-Score 0.211795
RoCo-Spring: The Robust Correspondence Challenge
The NeurIPS 2026 challenge on robust dense correspondence has concluded. Final Optical Flow, Stereo Matching, and Scene Flow standings are frozen.
Dense correspondence has made remarkable progress on standard benchmarks. Although modern Optical Flow, Stereo Matching, and Scene Flow methods achieve strong performance under ideal conditions, their accuracy can degrade substantially under real-world visual shifts.
Robustness under realistic corruptions remains a challenge for the deployment of these methods in autonomous driving, robotics, and other safety-critical settings. RoCo-Spring jointly evaluates clean accuracy and corrupted robustness, targeting methods that remain accurate under camera noise, adverse weather conditions, blur, compression, and changes in illumination.
Winners
Final Challenge Winners
Each winner is the complete scored method with the lowest RbS-Score. Standings were frozen at October 1, 2026, 23:59 Anywhere on Earth.
KoreaU_DLmath
RoCo-19 · CorrDrop-Stereo
RbS-Score 0.117581
KoreaU_DLmath
RoCo-19 · Q4-Independent
RbS-Score 0.241302
KoreaU_DLmath
RoCo-19 · Combined quantitative tracks
RbS-Score 0.262759
Leaderboard Preview
Top Three by Track
The best complete methods in the frozen final leaderboard. Teams without a complete score are not included.
Frozen at
Loading published standings…
Datasets
Spring and RobustSpring
Spring
Spring provides high-resolution stereo video with left and right images at 1920x1080 px, together with dense scene-flow ground truth at 4x super-resolution. It includes bidirectional disparities for stereo and depth, disparity changes for Scene Flow, and forward/backward Optical Flow for both left and right views. This makes Spring a unified high-detail benchmark for Optical Flow, Stereo Matching, and Scene Flow.
RobustSpring
RobustSpring extends Spring into a robustness benchmark with 20 realistic image corruptions, including blur, color changes, noise, quality degradations, and weather effects. The corruptions are applied to stereo video data and are integrated consistently over time, across stereo views, and with depth where applicable, enabling controlled robustness evaluation for Optical Flow, Stereo Matching, and Scene Flow.
Tracks
Four Challenge Tracks
Optical Flow
Estimate a dense 2D displacement field between consecutive frames, assigning each visible pixel a horizontal and vertical motion vector.
Stereo Matching
Estimate a dense disparity map from a rectified stereo image pair, assigning each pixel the horizontal offset to its corresponding point.
Scene Flow
Estimate dense 3D motion from stereo image sequences, combining per-pixel geometry and temporal motion into a single correspondence task.
Exploration Track
Submit a rigorous analysis of robustness in dense correspondence, focusing on failure modes, method behavior, metrics, or evaluation design.
Timeline
Competition Schedule
| Date | Milestone |
|---|---|
| July 2, 2026 | Website launch |
| July 13, 2026 | Development leaderboard opens for all quantitative tasks |
| September 25, 2026 NEW | Workshop paper submission deadline (4–6 main pages) |
| September 30, 2026 | Final quantitative submission deadline |
| October 06, 2026 | Workshop paper author notification |
| October 15, 2026 | Camera-ready paper, code, and reproducibility package deadline |
| October 15, 2026 | Final evaluation, reproducibility checks, and award shortlisting |
| October 31, 2026 | Winners notified and workshop program finalized |
| December 12, 2026 | In-person NeurIPS Competition Track workshop · Room MR C4.3 · 15:30–17:45 (Sydney local time) |
The quantitative challenge has concluded and its leaderboard is frozen. The workshop is on December 12, 2026.
Workshop
Confirmed Keynote Speakers
Jia Deng
Princeton University · Princeton Vision & Learning Lab
Jia Deng is Professor of Computer Science at Princeton University and Director of the Princeton Vision & Learning Lab. He brings a uniquely relevant perspective to RoCo-Spring: his work spans benchmark-driven computer vision, large-scale datasets such as ImageNet[1], and influential dense correspondence architectures across multiple tasks, including RAFT for Optical Flow[2], RAFT-Stereo for Stereo Matching[3], and SEA-RAFT for efficient and accurate Optical Flow[4]. His keynote will connect the evolution of correspondence methods and benchmark design with the central question of the challenge: how to turn clean benchmark progress into robust Optical Flow, Stereo Matching, and Scene Flow methods that remain reliable under realistic visual shifts.
Fatih Porikli
Qualcomm AI Research
Fatih Porikli is an IEEE Fellow and Vice President of Technology at Qualcomm AI Research. His expertise connects robust visual perception, video understanding, low-level vision, and real-world deployment. His prior work includes scene-flow estimation under degraded video conditions, including simultaneous stereo video deblurring and Scene Flow estimation[5], joint stereo video deblurring, scene flow estimation, and moving-object segmentation[6], and adversarial robustness for vision systems[7]. His talk will provide an industry-facing and deployment-oriented perspective on robust dense correspondence.
References
- Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A Large-Scale Hierarchical Image Database. Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 248–255.
- Teed, Z., & Deng, J. (2020). RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. Proc. European Conference on Computer Vision (ECCV), 402–419.
- Lipson, L., Teed, Z., & Deng, J. (2021). RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching. Proc. International Conference on 3D Vision (3DV), 218–227.
- Wang, Y., Lipson, L., & Deng, J. (2024). SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow. Proc. European Conference on Computer Vision (ECCV), 36–54.
- Pan, L., Dai, Y., Liu, M., & Porikli, F. (2017). Simultaneous Stereo Video Deblurring and Scene Flow Estimation. Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6987–6996.
- Pan, L., Dai, Y., Liu, M., Porikli, F., & Pan, Q. (2020). Joint Stereo Video Deblurring, Scene Flow Estimation and Moving Object Segmentation. IEEE Transactions on Image Processing (TIP), 29, 1748–1761.
- Naseer, M., Khan, S., Hayat, M., Khan, F. S., & Porikli, F. (2020). A Self-Supervised Approach for Adversarial Robustness. Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 262–271.
Schedule
Workshop Schedule
| Date | Time (Sydney local) | Location |
|---|---|---|
| December 12, 2026 | 15:30–17:45 | Room MR C4.3 |
Detailed program to be announced.
Organizers
Organizing Team
Shashank AgnihotriUniversity of Mannheim
Victor OeiUniversity of Stuttgart
Jenny SchmalfussNVIDIA
Katrin BauerUniversity of Stuttgart
Noah Berenguel SennUniversity of Stuttgart
Steffen JungUniversity of Mannheim
Henrique MorimitsuUniversity of Science and Technology Beijing
Andrés BruhnUniversity of Stuttgart
Margret KeuperUniversity of Mannheim and MPI-INF
Support
Sponsors & Acknowledgements
Event support
Sponsors
This event is supported by the SFB-TRR 161 Quantitative Methods for Visual Computing.
Research funding
Acknowledgements
Shashank Agnihotri and Margret Keuper acknowledge funding by the DFG Research Unit 5336 – Learning to Sense (L2S). Margret Keuper acknowledges funding by BMFTR project TrackOpt (01IS24074A-D). Andres Bruhn and Victor Oei acknowledge funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project-ID 251654672 – TRR 161: Quantitative Methods for Visual Computing (B04, A07). Katrin Bauer and Andres Bruhn acknowledge funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project-ID 533085500 – Robust Optical Flow. Katrin Bauer and Victor Oei acknowledge support from the International Max Planck Research School for Intelligent Systems (IMPRS-IS).
Contact
Get in Touch
Challenge email: roco-spring-org@googlegroups.com
GitHub Starter Kit: hmorimitsu/roco-spring-devkit
