Spring: L. Mehl, J. Schmalfuss, A. Jahedi, Y. Nalivayko, A. Bruhn — University of Stuttgart
RobustSpring: J. Schmalfuss, V. Oei, L. Mehl, M. Bartsch, S. Agnihotri, M. Keuper, A. Bruhn
Download
Stereo
Optical Flow
Scene Flow
Submit
FAQ
RAFT-Stereo
Nov. 1, 2022, 2 p.m. — Public
đŸ’¡ submitted by spring team | L. Lipson, Z. Teed, and J. Deng. "RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching." In International Conference on 3D Vision (3DV), 2021.
Code: https://github.com/princeton-vl/RAFT-Stereo/
Stereo
1px total
1px low-detail
1px high-detail
1px matched
1px unmatched
1px not sky
1px sky
1px s0-10
1px s10-40
1px s40+
15.273
14.983
32.774
13.394
52.582
9.924
96.571
22.588
10.018
17.086
Abs total
Abs low-detail
Abs high-detail
Abs matched
Abs unmatched
Abs not sky
Abs sky
Abs s0-10
Abs s10-40
Abs s40+
3.025
3.041
2.016
2.722
9.037
0.678
38.684
7.692
0.688
1.147
D1 total
D1 low-detail
D1 high-detail
D1 matched
D1 unmatched
D1 not sky
D1 sky
D1 s0-10
D1 s10-40
D1 s40+
8.626
8.647
7.318
7.400
32.966
3.670
83.934
17.763
4.686
3.055
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Reference Frame
Disparity 1 visualization
Disparity 1 error
Error visualization color code
Lukas Mehl, Jenny Schmalfuss, Azin Jahedi, Yaroslava Nalivayko, Andrés Bruhn:"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo ".In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Jenny Schmalfuss, Victor Oei, Lukas Mehl, Madlen Bartsch, Shashank Agnihotri, Margret Keuper, Andrés Bruhn:"RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo ".arXiv preprint arXiv:2505.09368, 2025
The Spring movie assets by Blender Foundation are licensed under CC BY 4.0 . The authors thank Andy Goralczyk, Francesco Siddi and the whole Blender Studio team. Lukas Mehl acknowledges funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – Project-ID 251654672 – TRR 161: Quantitative Methods for Visual Computing (B04). Jenny Schmalfuss and Azin Jahedi acknowledge support from the International Max Planck Research School for Intelligent Systems (IMPRS-IS).
Contact | Imprint | Privacy