Result details - ETH3D

Submitted by JUNHONG MIN.

Submission data

Full name	Confidence Aware Stereo Matching
Description	Our 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.
Parameters	feature dimension:128 refinement iterations: 3 4-level u-net transformer
Publication title	Confidence Aware Stereo Matching for Realistic Cluttered Scenario
Publication authors	Junhong Min, Youngpil Jeon
Publication venue	ICIP 2024 submissions (1861)
Programming language(s)	python
Hardware	Intel i9-13900K, Nvidia 4090
Submission creation date	5 Feb, 2024
Last edited	5 Feb, 2024

High-res multi-view results

Info	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.
No results yet.

Low-res many-view results

Info	all	low-res many-view	indoor	outdoor	lakeside	sand box	storage room	storage room 2	tunnel
No results yet.

Low-res two-view results

Info	all	deliv. area 1l	deliv. area 1s	deliv. area 2l	deliv. area 2s	deliv. area 3l	deliv. area 3s	elect. 1l	elect. 1s	elect. 2l	elect. 2s	elect. 3l	elect. 3s	facade 1s	forest 1s	forest 2s	playg. 1l	playg. 1s	playg. 2l	playg. 2s	playg. 3l	playg. 3s	terra. 1s	terra. 2s	terra. 1l	terra. 1s	terra. 2l	terra. 2s
	0.32	0.53	0.34	0.27	0.31	0.34	0.29	0.31	0.32	0.25	0.31	0.27	0.40	0.45	0.27	0.30	0.26	0.40	0.28	0.37	0.28	0.39	0.29	0.40	0.29	0.28	0.24	0.30

SLAM results

		all	boxes	boxes dark	buddha	cables 4	cables 5	desk 1	desk 2	desk changing 2	desk dark 1	desk dark 2	desk global light changes	desk ir light	dino	drone	foreground occlusion	helmet	kidnap 2	lamp	large loop 2	large loop 3	large non loop	motion 2	motion 3	motion 4	planar 1	reflective 2	scale change	table 1	table 2	table 5	table 6	table global light changes	table local light changes	table scene	trashbin
	Method	Info
No results yet.