AI Paper Atlas

Research map / 3D vision / Depth and stereo

Global Regulation and Excitation via Attention Tuning for Stereo Matching

Jiahao Li, Xinhong Chen, Zhengmin Jiang, Qian Zhou, Yung-Hui Li, Jianping Wang

ICCV 2025 · 3D vision › Depth and stereo · approach: Learned stereo with specialized sensors · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Volume Attention with a correlation cost volume (ablation)IGEV-Stereo · Scene Flow testEPE all (px): 0.479 -> 0.469Improved
replace correlation cost volume with concatenation cost volume under Volume Attention (ablation)IGEV-Stereo + VA · Scene Flow testEPE all (px): 0.469 -> 0.466Improved
add Spatial Attention to concatenation cost volume with Volume Attention (ablation)IGEV-Stereo + VA · Scene Flow testEPE occluded (px): 1.616 -> 1.587Improved
add Matching Attention (without VA or SA) to concatenation cost volume (ablation)IGEV-Stereo · Scene Flow testEPE non-occluded (px): 0.194 -> 0.153Improved
add SA and MA to Volume Attention (full model) (ablation)GREAT-IGEV · Scene Flow testEPE all (px): 0.466 -> 0.413Improved
integrate the GREAT attention modules into RAFT-StereoRAFT-Stereo · Scene Flow testEPE all (px): 0.551 -> 0.488Improved
integrate the GREAT attention modules into IGEV-StereoIGEV-Stereo · Scene Flow testEPE all (px): 0.479 -> 0.413Improved
integrate the GREAT attention modules into Selective-IGEVSelective-IGEV · Scene Flow testEPE all (px): 0.453 -> 0.419Improved
integrate the GREAT modules into IGEV-Stereo, occluded regionsIGEV-Stereo · Scene Flow testEPE occluded (px): 1.649 -> 1.514Improved
integrate the GREAT modules into IGEV-Stereo, non-occluded regionsIGEV-Stereo · Scene Flow testEPE non-occluded (px): 0.194 -> 0.135Improved
use GREAT attention modules with fewer iterationsGREAT-IGEV · Scene Flow testEPE all (px): 0.483 at 4 iterations vs 0.479 for IGEV-Stereo at 32Improved
integrate GREAT modules into RAFT-Stereo, zero-shot to KITTI 2015RAFT-Stereo · KITTI 2015 (zero-shot)3-pixel error (%): 5.8 -> 5.8No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy