AI Paper Atlas

Research map / 3D vision / Human pose estimation

Skeleton2Mesh: Kinematics Prior Injected Unsupervised Human Mesh Recovery

Zhenbo Yu, Junjie Wang, Jingwei Xu, Bingbing Ni, Chenglong Zhao, Minsi Wang, Wenjun Zhang

ICCV 2021 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 29 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 differentiable inverse kinematics (DIK) instead of learned pose regression (ablation)Skeleton2Mesh · Human3.6M testPMPJPE: 111.9 -> 55.4Improved
use DIK instead of iterative IK solver (ablation)Skeleton2Mesh · Human3.6Mmean joint angle error: 0.592 -> 0.391Improved
add adaptive joint regressor (ablation)Skeleton2Mesh · Human3.6M testPMPJPE: 63.7 -> 55.4Improved
add shape refinement (differentiable renderer) (ablation)Skeleton2Mesh · Human3.6M testPVE: 122.6 -> 120.8Improved
add shape refinement (differentiable renderer) (ablation)Skeleton2Mesh · Surreal valPVE: 112.9 -> 107.8Improved
add shape refinement (differentiable renderer) (ablation)Skeleton2Mesh · Surreal valMPJPE: 95.1 -> 99.5Hurt
add pose refinement (PR) module (ablation)Skeleton2Mesh · Surreal valPPVE: 82.5 -> 75.1Improved
add pose refinement (PR) module (ablation)Skeleton2Mesh · Human3.6M testPPVE: 81.4 -> 80.8Improved
add pose refinement (PR) module (ablation)Skeleton2Mesh · Surreal valjoint angle error: 0.325 -> 0.314Improved
refine all local rotations instead of only endpoint rotations in PR (ablation)Skeleton2Mesh DIK+PR · Human3.6Mmean joint angle error: 0.389 -> 0.404Hurt
apply temporal correction to discontinuous framesSkeleton2Mesh · Human3.6MPPVE: 81.98 -> 69.70Improved

Later papers that compared with this method

1 later accepted paper reports Skeleton2Mesh as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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