AI Paper Atlas

Research map / 3D vision / Depth and stereo

Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers

Chung-Shien Brian Wang, Christian Schmidt, Jens Piekenbrinck, Bastian Leibe

CVPR 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 29 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
replace dense global attention with training-free block-sparse attentionVGGT, π3, MapAnything · multi-view pose and pointmap benchmarkstask accuracy vs inference speed: more than 3× faster, comparable accuracyImproved
increase sparsity ratio of global attention (ablation)Sparse VGGT / π3 · relative pose estimation (RE10K, CO3Dv2, TUM, ScanNet)pose accuracyHurt
compute dense attention for special (camera/register) tokens (ablation)Block-sparse attention · CO3Dv2 / ETH3DAUC@30 / ChamferImproved
combine top-k with CDF thresholding instead of CDF-only (SpargeAttention) (ablation)Block-sparse attention · CO3Dv2 / ETH3DAUC@30 / ChamferImproved
random block masking instead of predicted block masks (ablation)Block-sparse attention · CO3Dv2 / ETH3DAUC@30 / ChamferHurt
add linear projection after pooling queries and keys (ablation)Block mask predictor · VGGTtask performanceNo clear effect
skip a single middle aggregator global-attention layer (ablation)VGGT · CO3Dv2AUC@30Hurt

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