Submitted by Nicolas Jourdan.

Submission data

Full nameGANet reference submission for robust vision challenge
DescriptionGANet reference submission as baseline for the
stereo benchmark of the robust vision challenge
2020.
All method credits go to the original author
(Zhang et al.)

We are formulating traditional geometric and
optimization of stereo into deep neural networks.
ParametersTrained on Middleburry, KITTI, ETH3D from the KITTI
checkpoint made available in the GANet repository
on Github by the original authors.
Frequency of sampling was adapted to the dataset
size. Test images scaled to next multiple of 48.
Publication titleGA-Net: Guided Aggregation Net for End- to-end Stereo Matching
Publication authorsZhang, Feihu and Prisacariu, Victor and Yang, Ruigang and Torr, Philip HS
Publication venueCVPR 2019
Publication URLhttps://github.com/feihuzhang/GANet
Programming language(s)Python (PyTorch), CUDA
HardwareIntel Core I9-9920X, Nvidia Quadro RTX 8000
Websitehttps://github.com/feihuzhang/GANet
Source code or download URLhttps://github.com/feihuzhang/GANet
Submission creation date17 Jul, 2020
Last edited17 Jul, 2020

High-res multi-view results



Infoallhigh-res
multi-view
indooroutdoorcourty.delive.electrofacadekickermeadowofficepipesplaygr.reliefrelief.terraceterrai.
No results yet.

Low-res many-view results



Infoalllow-res
many-view
indooroutdoorlakesidesand boxstorage roomstorage room 2tunnel
No results yet.

Low-res two-view results



Infoalldeliv. area 1ldeliv. area 1sdeliv. area 2ldeliv. area 2sdeliv. area 3ldeliv. area 3select. 1lelect. 1select. 2lelect. 2select. 3lelect. 3sfacade 1sforest 1sforest 2splayg. 1lplayg. 1splayg. 2lplayg. 2splayg. 3lplayg. 3sterra. 1sterra. 2sterra. 1lterra. 1sterra. 2lterra. 2s
permissivetwo views0.610.560.580.560.520.550.520.850.630.780.441.000.630.340.620.440.530.510.850.510.630.480.480.590.710.650.810.79

SLAM results



allboxesboxes darkbuddhacables 4cables 5desk 1desk 2desk changing 2desk dark 1desk dark 2desk global light changesdesk ir lightdinodroneforeground occlusionhelmetkidnap 2lamplarge loop 2large loop 3large non loopmotion 2motion 3motion 4planar 1reflective 2scale changetable 1table 2table 5table 6table global light changestable local light changestable scenetrashbin
MethodInfo
No results yet.