Robust Vision Challenge

Stereo Leaderboard

Method
Middlebury
(Detailed subrankings)
KITTI
(Detailed subrankings)
ETH3D
(Detailed subrankings)
1
CFNet_RVC
2
2
1
Submitted by Anonymous
2
NLCA_NET_v2_RVC
3
1
2
NLCA-Net: a non-local context attention network for stereo matching - Submitted by Zhibo Rao (Northwestern Polytechnical University)
3
HSM-Net_RVC
1
6
3
Hierarchical deep stereo matching on high-resolution images, CVPR 2019. [Project page] - Submitted by Gengshan Yang (CMU)
4
CVANet_RVC
5
3
4
Submitted by Haoyu Ren (Samsung Semiconductor Inc)
5
AANet_RVC
6
5
5
AANet: Adaptive Aggregation Network for Efficient Stereo Matching [Project page] - Submitted by Haofei Xu (University of Science and Technology of China)
6
GANetREF_RVC
7
4
6
Baseline - Submitted by Nicolas Jourdan (RVC Team)
7
SGM_RVC
4
7
7
Baseline - Submitted by Heiko Hirschmueller (Roboception GmbH)
8
ELAS_RVC
8
8
8
Baseline - Submitted by Thomas Schöps (RVC Team)
STTRV1_RVC
✓
✓
[incomplete submission] Submitted by Anonymous
Last update: 2020-08-26 19:02:43 CET
Joining multiple rankings into one in a fair manner is a non-trivial task. In electorial science the equivalent task of finding one consensus ordering based on many ordered votes has been a central question for many years. The currently most-accepted solution for this problem is the Schulze Proportional Ranking (PR) method [1] for sorted lists of winners. We are using Schulze PR to rank the top ten in each challenge. The software used for this is a fork of the pyvotecore implemenation which you can find here.

[1] Markus Schulze. "A new monotonic, clone-independent, reversal symmetric, and condorcet-consistent single-winner election method". In Social Choice and Welfare. 2011.

We first rank each method according to a representative subset of metrics per dataset and then rank the resulting ranks to yield one global rank. The metrics and rankings per dataset can be viewed by clicking on "Detailed subrankings". Note that these rankings may differ from the rankings on the original websites as those typically consider a single metric while we are looking for robustness and thus take a number of metrics per dataset into account.


Sponsors

Gold Sponsors


Silver Sponsors



eXTReMe Tracker