Spring Dataset and Benchmark Logo

Spring: L. Mehl, J. Schmalfuss, A. Jahedi, Y. Nalivayko, A. Bruhn — University of Stuttgart

RobustSpring: V. Oei, J. Schmalfuss, L. Mehl, M. Bartsch, S. Agnihotri, M. Keuper, A. Bulling, A. Bruhn — University of Stuttgart, University of Mannheim, MPI for Informatics

Not logged in | Login | Create Account

Show: All | Accuracy | Robustness

💡 Please note that methods marked "submitted by spring team" have not been finetuned on Spring.

Name 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+ 		Abs D1 robust
Δ1px 		robust
ΔAbs 		robust
ΔD1
 
1
RoCo-22_StableBridge  
7.135 6.824 25.908 5.940 30.861 7.371 3.554 2.936 7.757 13.244 0.471 2.705 22.529 2.386 4.427
 
2
CroCo-Stereo   code
7.135 6.824 25.893 5.940 30.855 7.371 3.550 2.934 7.757 13.247 0.471 2.705 n/a n/a n/a
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow. Weinzaepfel et al. ICCV 2023.
3
MS-RAFT-3D [SF]   code
7.135 6.824 25.893 5.940 30.857 7.371 3.551 2.934 7.757 13.247 0.471 2.705 n/a n/a n/a
J. Schmid, A. Jahedi, N. Berenguel Senn and A. Bruhn. "MS-RAFT-3D: A Multi-scale Architecture for Recurrent Image-based Scene Flow". ICIP 2025.
4
MS-RAFT-3D+ [SF]   code
7.135 6.824 25.893 5.940 30.857 7.371 3.551 2.934 7.757 13.247 0.471 2.705 n/a n/a n/a
J. Schmid, A. Jahedi, N. Berenguel Senn and A. Bruhn. "MS-RAFT-3D: A Multi-scale Architecture for Recurrent Image-based Scene Flow". ICIP 2025.
5
RoCo-19-Q4-Independent [SF]  
8.759 8.448 27.521 7.408 35.577 8.901 6.603 5.242 9.340 13.693 0.568 3.217 n/a n/a n/a
 
6
IInet  
10.003 9.630 32.504 8.457 40.707 10.305 5.420 5.865 10.761 15.590 0.761 3.784 n/a n/a n/a
Anonymous.
7
Reg-Stereo  
10.328 9.925 34.598 8.864 39.387 10.531 7.232 6.076 9.599 20.566 0.864 4.028 n/a n/a n/a
Anonymous.
8
RoCo-19-DEFOM2K-DPFlow [SF]  
11.179 10.886 28.861 9.603 42.478 8.592 50.500 13.376 8.796 14.127 0.671 3.763 n/a n/a n/a
 
9
VHS  
13.726 13.368 35.317 11.646 55.022 12.618 30.565 12.106 13.249 18.223 4.235 5.940 n/a n/a n/a
M. Plack, H. Dröge, L. Van Holland and M. B. Hullin. "VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors". WACV 2025.
10
ACVNet   code
14.772 14.432 35.273 12.600 57.894 11.163 69.621 18.386 11.346 18.145 1.516 5.346 36.800 15.790 16.810
💡 submitted by spring team | G. Xu, J. Cheng, P. Guo, and X. Yang. "Attention Concatenation Volume for Accurate and Efficient Stereo Matching." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
11
LTNet  
15.244 14.949 33.016 13.181 56.201 10.373 89.264 21.231 11.307 15.637 0.825 3.912 n/a n/a n/a
Anonymous.
12
RAFT-Stereo   code
15.273 14.983 32.774 13.394 52.582 9.924 96.571 22.588 10.018 17.086 3.025 8.626 33.400 16.570 11.840
💡 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.
13
RoCo-Spring Team Baselines-Stereo  
15.561 15.270 33.132 13.636 53.781 10.165 97.567 23.005 10.415 16.803 3.875 8.844 35.409 18.908 14.037
💡 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.
14
RoCo-Spring Team Baselines-Scene Flow [SF]  
15.561 15.270 33.132 13.636 53.781 10.165 97.567 23.005 10.415 16.803 3.875 8.844 n/a n/a n/a
💡 submitted by spring team | Z. Teed, and J. Deng. "RAFT-3D: Scene Flow using Rigid-Motion Embeddings." In CVPR, 2021. and L. Lipson, Z. Teed, and J. Deng. "RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching." In 3DV, 2021.
15
Gunjan Haldar  
16.113 15.696 41.274 13.478 68.430 16.002 17.805 11.354 14.876 28.832 1.641 5.905 n/a n/a n/a
 
16
RoCo-43_FineAtten  
16.113 15.696 41.274 13.478 68.430 16.002 17.805 11.354 14.876 28.832 1.641 5.905 n/a n/a n/a
Anonymous.
17
PWOC-3D [SF]   code
18.226 17.831 42.067 16.020 62.014 15.946 52.877 18.279 12.716 34.570 1.343 5.887 n/a n/a n/a
R. Saxena, R. Schuster, O. Wasenmuller, and D. Stricker. "PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow Estimation." In IEEE Intelligent Vehicles Symposium (IV), 2019.
18
Roco_19_RAFTStereo_Scale040_new  
19.744 19.457 37.066 17.612 62.086 14.705 96.336 25.279 13.606 27.568 1.077 5.204 n/a n/a n/a
Anonymous.
19
LEAStereo   code
19.888 19.547 40.396 17.611 65.086 16.735 67.805 19.076 13.861 39.412 3.884 9.194 40.950 21.900 20.770
💡 submitted by spring team | X. Cheng, Y. Zhong, M. Harandi, Y. Dai, X. Chang, H. Li, T. Drummond, and Z. Ge. "Hierarchical Neural Architecture Search for Deep Stereo Matching." In NeurIPS, 2020.
20
M-FUSE (F) [SF]   code
19.888 19.547 40.396 17.611 65.086 16.735 67.805 19.076 13.861 39.412 3.884 9.194 n/a n/a n/a
💡 submitted by spring team | L. Mehl, A. Jahedi, J. Schmalfuss, and A. Bruhn. "M-FUSE: Multi-frame Fusion for Scene Flow Estimation." In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.
21
SplatFlow3D (C+T) + LEAStereo (Things); Two-frame [SF]   code
19.888 19.547 40.396 17.611 65.086 16.735 67.805 19.076 13.861 39.412 3.884 9.194 n/a n/a n/a
 
22
GANet   code
23.225 22.912 42.064 20.976 67.878 18.418 96.274 24.286 16.427 41.499 4.594 10.393 45.260 12.110 17.930
💡 submitted by spring team | F. Zhang, V. Prisacariu, R. Yang, and P. HS Torr. "GA-Net: Guided Aggregation Net for End-to-end Stereo Matching." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
23
RAFT-3D (F) [SF]   code
23.225 22.912 42.064 20.976 67.878 18.418 96.274 24.286 16.427 41.499 4.594 10.393 n/a n/a n/a
💡 submitted by spring team | Z. Teed, and J. Deng. "RAFT-3D: Scene Flow using Rigid-Motion Embeddings." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
24
CamLiFlow (F) [SF]   code
23.225 22.912 42.064 20.976 67.878 18.418 96.274 24.286 16.427 41.499 4.594 10.393 n/a n/a n/a
💡 submitted by spring team | H. Liu, T. Lu, Y. Xu, J. Liu, W. Li, and L. Chen. "CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
25
GANet (K)  
27.912 27.732 38.811 25.560 74.617 23.282 98.285 38.298 20.155 31.369 5.287 11.561 44.710 6.440 10.860
💡 submitted by spring team | F. Zhang, V. Prisacariu, R. Yang, and P. HS Torr. "GA-Net: Guided Aggregation Net for End-to-end Stereo Matching." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
26
CamLiFlow (K) [SF]   code
32.309 32.096 45.189 30.071 76.734 27.963 98.355 39.354 22.522 48.158 7.042 14.174 n/a n/a n/a
💡 submitted by spring team | H. Liu, T. Lu, Y. Xu, J. Liu, W. Li, and L. Chen. "CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
27
RAFT-3D (K) [SF]   code
32.309 32.096 45.189 30.071 76.734 27.963 98.355 39.354 22.522 48.158 7.042 14.174 n/a n/a n/a
💡 submitted by spring team | Z. Teed, and J. Deng. "RAFT-3D: Scene Flow using Rigid-Motion Embeddings." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
28
LEAStereo (K)  
47.496 47.429 51.562 45.766 81.844 44.063 99.669 78.982 31.228 36.339 6.145 17.163 50.020 8.240 14.040
💡 submitted by spring team | X. Cheng, Y. Zhong, M. Harandi, Y. Dai, X. Chang, H. Li, T. Drummond, and Z. Ge. "Hierarchical Neural Architecture Search for Deep Stereo Matching." In NeurIPS, 2020.
29
M-FUSE (K) [SF]   code
52.232 52.185 55.051 50.647 83.685 49.104 99.771 80.774 34.056 52.347 7.890 19.836 n/a n/a n/a
💡 submitted by spring team | L. Mehl, A. Jahedi, J. Schmalfuss, and A. Bruhn. "M-FUSE: Multi-frame Fusion for Scene Flow Estimation." In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.