Entity · other

multi-view 3D reconstruction

otheractivemulti-view-3d-reconstruction-31fc519c·1 events·first seen May 25, 2026

Aliases: multi-view 3D reconstruction

Co-occurring entities

inter-frame token selection visual geometry transformer global attention Good Token Hunting intra-frame entropy-guided sparsification intra-frame token sparsification

More like this (12)

online 3D reconstruction 4D reconstruction Multiview Counting MPI3D SM4RT: Learning Structured Motion Geometry for 4D Reconstruction monocular depth estimation HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration Hunyuan 3D 3D optical flow HumanML3D 3D-Aware VLMs with Implicit and Explicit Geometries 3D Medical Image Classification

Recent events (1)

5arXiv · cs.LG·May 25, 2026·source ↗

Good Token Hunting: Token Selection Framework for Visual Geometry Transformers

This paper introduces a two-stage token selection framework to address the quadratic computational scaling of global attention in visual geometry transformers used for multi-view 3D reconstruction. The approach combines diversity-based inter-frame selection (frame-level) with entropy-guided intra-frame sparsification (token-level within frames). Experiments demonstrate over 85% acceleration for 500-image scenes while maintaining or improving baseline reconstruction quality, offering a favorable speed-accuracy trade-off.

Inference Economics Agent and Tool Ecosystem inter-frame token selection visual geometry transformer global attention +5 more