Result details - ETH3D

Submitted anonymously.

Submission data

Full name	Scalable Stereo Matching Model
Description	transformer based stereo matching using stacked multi-resolution vision transformer blocks
Parameters	3 multi-resolution vision transformer blocks with base channel dimension 256
Programming language(s)	Torch
Hardware	Intel i9-13900K, Nvidia 4090
Submission creation date	3 Mar, 2025
Last edited	8 Mar, 2025

High-res multi-view results

Info	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.
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	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
	0.46	0.39	1.17	0.37	0.17	1.14	0.01	1.46	1.83	0.19	0.87	0.13	0.19	0.57	0.43	0.01	0.01	0.00	0.00	0.21	0.00

SLAM results

		all	cables 1	cables 2	cables 3	camera shake 1	camera shake 2	camera shake 3	ceiling 1	ceiling 2	desk 3	desk changing 1	einstein 1	einstein 2	einstein dark	einstein flashlight	einstein global light changes 1	einstein global light changes 2	einstein global light changes 3	kidnap 1	kidnap dark	large loop 1	mannequin 1	mannequin 3	mannequin 4	mannequin 5	mannequin 7	mannequin face 1	mannequin face 2	mannequin face 3	mannequin head	motion 1	planar 2	planar 3	plant 1	plant 2	plant 3	plant 4	plant 5	plant dark	plant scene 1	plant scene 2	plant scene 3	reflective 1	repetitive	sfm bench	sfm garden	sfm house loop	sfm lab room 1	sfm lab room 2	sofa 1	sofa 2	sofa 3	sofa 4	sofa dark 1	sofa dark 2	sofa dark 3	sofa shake	table 3	table 4	table 7	vicon light 1	vicon light 2
	Method	Info
No results yet.