AI Paper Atlas

Research map / 3D vision / 3D generation

VoxAnchor: Explicit Voxel-Semantic Grounding for Spatial Understanding in Videos

Xinglin Li, TingTing Long, Jingzhi Zhou, Chuxuan Zeng, Jiajing Chen, Jian Yang, Jin Xie

ECCV 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 0 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 Depth Anything 3 geometric features to Qwen3-VL-SFT (ablation)Qwen3-VL-4B · VSTI-Bench (3D foundation model ablation)average score: 54.4 -> 63.0Improved
use DA3 instead of VGGT (ablation)VoxAnchor · VSTI-Bench (3D foundation model ablation)average score: 59.5 -> 63.0Improved
use DA3 instead of IGGT (ablation)VoxAnchor · VSTI-Bench (3D foundation model ablation)average score: 60.7 -> 63.0Improved
replace standard cross-attention with Voxel-Aware Attention (ablation)VoxAnchor · VSTI-Bench (component ablation)average score: 63.0 -> 64.5Improved
add Geo-Semantic Adapter (ablation)VoxAnchor · VSTI-Bench (component ablation)average score: 64.5 -> 66.3Improved
add Voxel-Aware Attention (ablation)VoxAnchor · VSTI-Bench (component ablation)camera-object absolute distance: 40.0 -> 39.4Hurt
add Voxel-Aware Attention (ablation)VoxAnchor · VSTI-Bench (component ablation)camera movement direction: 73.2 -> 79.2Improved
add Geo-Semantic Adapter (ablation)VoxAnchor · VSTI-Bench (component ablation)camera-object relative distance: 73.0 -> 71.9Hurt
VoxAnchor-4B vs larger VLM-3R-7BVoxAnchor · VSTI-Benchaverage score: 58.8 -> 66.3Improved
VoxAnchor-4B vs GS-Reasoner-7B on VSIVoxAnchor · VSI-Benchaverage score: 64.7 -> 66.8Improved
VoxAnchor-4B vs GS-Reasoner-7B on absolute distanceVoxAnchor · VSI-Bench (Abs. Dist.)MRA: 61.9 -> 52.6Hurt

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