List your company
ResearchFormerly WizWand

Stereo Matching on Middlebury half-resolution v3

9.4Bad Pixel Error (0.5)MatchAttentionXL
7.209221.997136.78551.5729Oct 16, 2025
Updated 4mo ago

Evaluation results

MethodLinks
MatchAttentionXLTraining Data=Million-scale2025.109.43.711.89
Fast-FSD-416Training Data=Million-scale, Max Disparity=4162025.1011.84.812.2
Fast-FSD-192Training Data=Million-scale, Max Disparity=1922025.1013.777.354.79
Monster++-416Training Data=Million-scale, Max Disparity=4162025.1016.066.222.13
Zero-RAFT-StereoTraining Data=Million-scale2025.1016.748.324.45
MatchAttentionRTTraining Data=Million-scale2025.1017.17.553.76
RT-IGEV-416Training Data=Scene Flow, Max Disparity=4162025.1025.615.579.76
RT-Monster++-416Training Data=Million-scale, Max Disparity=4162025.1026.3413.16.16
RT-IGEV-192Training Data=Scene Flow, Max Disparity=1922025.1026.4916.9511.52
MatchAttentionRTTraining Data=Scene Flow2025.1027.0414.298.01
RT-Monster++-192Training Data=Million-scale, Max Disparity=1922025.1027.114.247.43
LiteAnyStereoTraining Data=Million-scale2025.103619.0210.39
IINetTraining Data=Scene Flow2025.1041.3125.6416.37
LiteAnyStereoTraining Data=Scene Flow2025.1045.6327.2715.75
LightStereo-LTraining Data=Scene Flow2025.1056.3337.2723.89
BANet-2DTraining Data=Scene Flow2025.1063.1543.7828.46
BANet-3D-192Training Data=Scene Flow, Max Disparity=1922025.1063.344.9130.12
BANet-3D-416Training Data=Scene Flow, Max Disparity=4162025.1064.1746.1631.42