Submitted by JUNHONG MIN.

Submission data

Full nameConfidence Aware Stereo Matching
DescriptionOur approach estimates disparities using implicitly inferred confidence levels. This capability is facilitated by our newly developed U-net transformer, which incorporates various attention mechanisms to extract global and local contexts from rectified image pairs.
Parametersfeature dimension:128
refinement iterations: 3
4-level u-net transformer
Publication titleConfidence Aware Stereo Matching for Realistic Cluttered Scenario
Publication authorsJunhong Min, Youngpil Jeon
Publication venueICIP 2024 submissions (1861)
Programming language(s)python
HardwareIntel i9-13900K, Nvidia 4090
Submission creation date5 Feb, 2024
Last edited5 Feb, 2024

High-res multi-view results



Infoallhigh-res
multi-view
indooroutdoorbotani.boulde.bridgedoorexhibi.lectur.living.loungeobserv.old co.statueterrac.
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
two views0.320.530.340.270.310.340.290.310.320.250.310.270.400.450.270.300.260.400.280.370.280.390.290.400.290.280.240.30

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.