AI Paper Atlas

Research map / 3D vision / Depth and stereo

AVGGT: Rethinking Global Attention for Accelerating VGGT

Xianbing Sun, Zhikai Zhu, Zhengyu Lou, Bo Yang, Jinyang Tang, Liqing Zhang, He Wang, Jianfu Zhang

CVPR 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 10 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
convert early global attention layers to frame attention (ablation)VGGT · RealEstate10K (10 frames)AUC@5: 63.176 -> 62.826No clear effect
replace early global K/V with a single mean token (ablation)VGGT · RealEstate10K (10 frames)AUC@5: 63.176 -> 61.788No clear effect
keep last global attention layers (not converted to frame attention) (ablation)AVGGT(2) · RealEstate10K (10 frames)AUC@5: 59.637 -> 61.959Improved
subsample queries too (nearest query) (ablation)AVGGT(2) · RealEstate10K (10 frames)AUC@5: 59.583 -> 42.565Hurt
subsample queries too (global-mean query) (ablation)AVGGT(2) · RealEstate10K (10 frames)AUC@5: 59.583 -> 26.973Hurt
select K/V tokens on a fixed grid instead of SIFT keypoints (ablation)AVGGT(2) · RealEstate10K (10 frames)AUC@5: 55.438 -> 61.959Improved
select K/V tokens on a fixed grid instead of randomly (ablation)AVGGT(2) · RealEstate10K (10 frames)AUC@5: 57.849 -> 61.959Improved
add diagonal preservation and mean component to subsampling (ablation)AVGGT(2) · 7-Scenes (333 frames)AUC@5: 24.539 -> 26.061Improved
add diagonal preservation and mean component to subsampling (ablation)AVGGT(2) · RealEstate10K (10 frames)AUC@5: 61.908 -> 61.959No clear effect
keep first-frame tokens uncompressed (ablation)AVGGT(4) · RealEstate10K (10 frames)AUC@5: 55.570 -> 59.583Improved
increase subsampling factor from 2 to 9 (ablation)AVGGT · RealEstate10K (10 frames)AUC@5: 61.959 -> 53.257Hurt
increase subsampling factor from 2 to 9 (ablation)A_pi3 · RealEstate10K (10 frames)AUC@5: 64.832 -> 40.437Hurt

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