Result details - ETH3D

Submitted by yaqi zou.

Submission data

Full name	Cost-Conditioned Multi-Receptive-Field Residual Aggregation for Stereo Matching
Description	CMRA-Stereo is a stereo matching framework developed for accurate and efficient depth estimation in challenging visual environments. Our research focuses on robust stereo perception, including applications in underwater robotics. We submit our results to the ETH3D two-view stereo benchmark to evaluate the method on real-world stereo images and compare its performance with existing approaches. This submission is part of our academic research.
Programming language(s)	Python with CUDA (PyTorch)
Hardware	NVIDIA GeForce RTX 4090 (24 GB VRAM), single GPU
Submission creation date	9 Sep, 2026
Last edited	9 Sep, 2026

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	delivery area	electro	forest	playground	terrains
No results yet.

Low-res two-view results

Info	all	lakes. 1l	lakes. 1s	sand box 1l	sand box 1s	stora. room 1l	stora. room 1s	stora. room 2l	stora. room 2s	stora. room 2 1l	stora. room 2 1s	stora. room 2 2l	stora. room 2 2s	stora. room 3l	stora. room 3s	tunnel 1l	tunnel 1s	tunnel 2l	tunnel 2s	tunnel 3l	tunnel 3s
	1.19	0.34	2.27	0.37	1.01	1.85	0.01	3.97	4.10	0.25	0.73	0.82	0.76	6.29	0.96	0.02	0.03	0.00	0.02	0.02	0.06

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.