AI Paper Atlas

Research map / 3D vision / Face and shape

POSEFusion: Pose-Guided Selective Fusion for Single-View Human Volumetric Capture

CVPR 2021 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 30 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use dynamic programming instead of greedy keyframe selectionPOSEFusion · Whole sequencemean multi-view depth fitting error (cm): 0.7732 -> 0.7507Helped
Remove pose energy from keyframe selection (ablation)POSEFusion · Human RGBD sequencesmulti-view depth fitting errorHurt
Remove visibility energy from keyframe selection (ablation)POSEFusion · Human RGBD sequencesmulti-view depth fitting errorHurt
Use per-frame keyframe selection instead of joint selection (ablation)POSEFusion · Adjacent video framestemporal coherence of invisible detailsHurt
Use greedy selection instead of global dynamic programming (ablation)POSEFusion · Whole sequencephysical plausibility of invisible detailsHurt

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