Submitted by Hailong Pan.

Submission data

Full nameAdaptive stereo matching method guided by learning
DescriptionOur approach is designed to reduce the time required for matching. First, the label of each pixel is learned by CNN. Then we determines whether the pixel should be matched and the matching parameters according to the label to reduce the time required for matching.
Programming language(s)C++ with CUDA
HardwareGeForce GTX 2080ti
Submission creation date29 Aug, 2019
Last edited29 Aug, 2019

High-res multi-view results



Infoallhigh-res
multi-view
indooroutdoorcourty.delive.electrofacadekickermeadowofficepipesplaygr.reliefrelief.terraceterrai.
binary2288.902080.732531.772485.982757.872974.474914.622255.54804.631611.14842.302657.832056.921960.621353.093080.73

Low-res many-view results



Infoalllow-res
many-view
indooroutdoordelivery areaelectroforestplaygroundterrains
No results yet.

Low-res two-view results



Infoalllakes. 1llakes. 1ssand box 1lsand box 1sstora. room 1lstora. room 1sstora. room 2lstora. room 2sstora. room 2 1lstora. room 2 1sstora. room 2 2lstora. room 2 2sstora. room 3lstora. room 3stunnel 1ltunnel 1stunnel 2ltunnel 2stunnel 3ltunnel 3s
No results yet.

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.