Spring Dataset and Benchmark Logo

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

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-det. 		1px
high-det. 		1px
matched 		1px
unmat. 		1px
rigid 		1px
non-rig. 		1px
not sky 		1px
sky 		1px
s0-10 		1px
s10-40 		1px
s40+ 		SF 1px D1 1px D2 1px Fl robust
1px D1 		robust
Abs D1 		robust
D1 		robust
1px D2 		robust
Abs D2 		robust
D2 		robust
EPE Fl 		robust
Fl Fl 		robust
1px Fl
 
1
MS-RAFT-3D+  
9.128 8.494 40.306 7.323 32.441 6.180 31.431 9.432 4.500 2.395 6.928 22.025 3.467 7.135 7.244 3.520 n/a n/a n/a n/a n/a n/a n/a n/a n/a
Anonymous.
2
MS-RAFT-3D  
9.283 8.652 40.299 7.442 33.066 6.337 31.564 9.507 5.873 2.434 6.990 22.547 3.433 7.135 7.291 3.703 n/a n/a n/a n/a n/a n/a n/a n/a n/a
Anonymous.
3
SplatFlow3D (C+T) + LEAStereo (Things); Two-frame   code
24.752 24.071 58.253 21.571 65.837 20.663 55.685 21.026 81.372 21.571 14.817 54.306 11.417 19.888 14.999 9.203 n/a n/a n/a n/a n/a n/a n/a n/a n/a
 
4
PWOC-3D   code
26.714 26.031 60.302 23.420 69.262 21.780 64.043 24.049 67.216 22.622 15.982 59.331 9.990 18.226 18.979 14.461 n/a n/a n/a n/a n/a n/a 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.
5
M-FUSE (F)   code
34.896 34.298 64.324 32.028 71.943 29.810 73.377 31.355 88.712 29.890 23.911 69.148 16.103 19.888 24.256 20.374 n/a n/a n/a n/a n/a n/a 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.
6
RAFT-3D (K)   code
37.262 36.796 60.227 34.340 75.021 32.866 70.522 33.231 98.531 43.799 24.546 63.914 17.345 32.309 32.948 13.962 n/a n/a n/a n/a n/a n/a 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.
7
CamLiFlow (F)   code
50.083 49.640 71.884 47.795 79.636 46.754 75.267 46.848 99.252 31.115 42.699 89.550 34.151 23.225 44.104 24.012 n/a n/a n/a n/a n/a n/a 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.
8
M-FUSE (K)   code
62.490 62.291 72.306 60.574 87.247 60.385 78.416 60.032 99.850 82.966 49.200 75.963 25.232 52.232 57.029 20.979 n/a n/a n/a n/a n/a n/a 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.
9
RAFT-3D (F)   code
78.822 78.753 82.195 78.329 85.191 79.618 72.799 77.570 97.838 84.329 81.680 65.478 66.879 23.225 73.426 48.066 n/a n/a n/a n/a n/a n/a 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.
10
CamLiFlow (K)   code
85.310 85.180 91.671 84.463 96.246 84.181 93.853 84.346 99.956 65.159 87.845 99.861 70.870 32.309 76.319 69.685 n/a n/a n/a n/a n/a n/a 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.