AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Human Mesh Estimation From Virtual Markers

Xiaoxuan Ma, Jiajun Su, Chunyu Wang, Wentao Zhu, Yizhou Wang

CVPR 2023 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 57 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
Use learned virtual markers instead of skeleton joints (ablation)Ours · H3.6MMPVE: 64.4 -> 58.0Improved
Use learned virtual markers instead of skeleton joints (ablation)Ours · SURREALMPVE: 53.6 -> 44.7Improved
Learn the virtual markers rather than selecting 64 vertices randomly (ablation)Ours · H3.6MMPVE: 63.0 -> 58.0Improved
Learn the virtual markers rather than selecting 64 vertices randomly (ablation)Ours · SURREALMPVE: 50.1 -> 44.7Improved
Increase marker count from 16 to 96 with ground-truth marker positions (ablation)Virtual marker mesh reconstruction · H3.6MMPVE: 46.8 -> 9.9Improved
Increase detected marker count from 64 to 96 (ablation)Ours · H3.6MMPVE: 58.0 -> 59.6Hurt
Use confidence-conditioned updated coefficients instead of a fixed coefficient matrix (ablation)Ours · H3.6M testMPVE: 64.7 -> 58.0Improved
Use confidence-conditioned updated coefficients instead of a fixed coefficient matrix (ablation)Ours · H3.6M testMPJPE: 51.6 -> 47.3Improved
Add confidence loss (ablation)Ours · H3.6M testMPVE: 59.2 -> 58.0Improved
Add pose loss (ablation)Ours · H3.6M testMPVE: 58.3 -> 58.0Improved
Add normal surface loss (ablation)Ours · H3.6M testMPVE: 60.6 -> 58.0Improved
Add edge surface loss (ablation)Ours · H3.6M testMPVE: 60.4 -> 58.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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