AI Paper Atlas

Research map / 3D vision / 3D generation

Geometry-Guided 3D Visual Token Pruning for Video-Language Models

Han Li, Zehao Huang, Jiahui Fu, Naiyan Wang, Si Liu

CVPR 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 2 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 inter-voxel spatial diversity pruning (SDP) to VCP (ablation)Geo3DPruner · 16 frames, 90% prunedavg performance retained: 89.4% -> 94.0%Improved
add intra-voxel view consistency pruning (VCP) to SDP (ablation)Geo3DPruner · 16 frames, 90% prunedavg performance retained: 91.3% -> 94.0%Improved
use iterative SDP instead of random voxel selection (ablation)Geo3DPruner · 16 frames, 90% prunedavg performance retained: 85.2% -> 94.0%Improved
use iterative SDP instead of uniform voxel selection (ablation)Geo3DPruner · 16 frames, 90% prunedavg performance retained: 85.4% -> 94.0%Improved
use attention from geometry encoder instead of cosine similarity for cross-frame relevance (ablation)Geo3DPruner · 16 frames, 90% prunedavg performance retained: 89.9% -> 94.0%Improved
Geo3DPruner instead of VisPruner at 90% pruningVideo-3D LLM · 16 framesavg performance retained: 84.9% -> 92.1%Improved
Geo3DPruner instead of FastV at 90% pruningVideo-3D LLM · 32 framesavg performance retained: 82.4% -> 92.0%Improved
Geo3DPruner instead of VisPruner at 90% pruningVideo-3D LLM · 8 framesavg performance retained: 81.6% -> 88.7%Improved
Geo3DPruner instead of VisPruner on dense captioning at 90% pruningVideo-3D LLM · Scan2Cap C@0.5, 16 framesCIDEr@0.5: 57.3 -> 80.3Improved
use 16 frames with 50% pruning instead of 8 frames unpruned at equal 1568 tokensGeo3DPruner · fixed token budgetavg performance: 100% -> 108%Improved
use 32 frames with 75% pruning instead of 8 frames unpruned at equal 1568 tokensGeo3DPruner · fixed token budgetavg performance: 100% -> 109%Improved
raise pruning ratio from 60% to 90%Geo3DPruner · 16 framesavg performance retained: 98.9% -> 92.1%Hurt

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