Robust Vision Challenge

Stereo Leaderboard

Method
Middlebury
(Detailed subrankings)
KITTI
(Detailed subrankings)
ETH3D
(Detailed subrankings)
1
iResNet_ROB
6
2
2
Learning for Disparity Estimation through Feature Constancy [Project page] - Submitted by Zhengfa Liang (National University of Defense Technology)
2
DN-CSS_ROB
3
7
1
Submitted by Tonmoy Saikia (University of Freiburg)
3
DLCB_ROB
5
4
3
Submitted by Sebastien Drouyer (CMLA - ENS Cachan)
4
NaN_ROB
2
5
9
Submitted by Yao Lu (Australian National University)
4
PSMNet_ROB
10
1
5
Pyramid Stereo Matching Network [Project page] - Submitted by Hsiao-Chien Yang (National Chiao Tung University (NCTU))
6
NOSS_ROB
1
16
4
Submitted by Anonymous
7
LALA_ROB
11
3
8
Submitted by Anonymous
8
CBMV_ROB
4
11
7
CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation [Project page] - Submitted by Konstantinos Batsos (Stevens Institute of Technology)
8
XPNet_ROB
8
8
6
Submitted by Anonymous
10
FBW_ROB
14
6
12
Submitted by ()
11
SGM_ROB
7
13
13
Stereo Processing by Semi-Global Matching and Mutual Information [Project page] - Submitted by Heiko Hirschmueller (Roboception GmbH)
12
MSMD_ROB
13
9
15
Submitted by Anonymous
12
PDISCO_ROB
16
10
11
Submitted by Anonymous
12
PWCDC_ROB
14
12
10
Submitted by Anonymous
15
WCMA_ROB
12
14
13
Submitted by yifan zhang (University of Science and Technology of China)
16
ELAS_ROB
9
16
16
Baseline - Submitted by Thomas Schöps (ROB Team)
17
DPSimNet_ROB
17
15
17
Submitted by Anonymous
Last update: 2018-11-15 00:12:57 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.


Gold Sponsors

Silver Sponsors



eXTReMe Tracker