AI Paper Atlas

Research map / 3D vision / Human pose estimation

PyMAF-X: Towards Well-Aligned Full-Body Model Regression From Monocular Images

Hongwen Zhang, Yating Tian, Yuxiang Zhang, Mengcheng Li, Liang An, Zhenan Sun, Yebin Liu

TPAMI 2023 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 166 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 mesh-aligned feedback (PyMAF) over baseline, ResNet-50HMR-style baseline · 3DPW and Human3.6MMPJPE: reduces MPJPE by 4.7 mm and 5.5 mmImproved
add mesh-aligned feedback (PyMAF) over baseline, ResNet-50HMR-style baseline · COCO val keypointsAP: 33.7 -> 42.2Improved
use mesh-aligned features instead of global features (ablation)PyMAF · Human3.6MMPJPE: 84.1 -> 79.6Improved
use mesh-aligned features instead of grid features (ablation)PyMAF (pyramidal) · Human3.6MMPJPE: 79.7 -> 76.8Improved
add feature pyramid to mesh-aligned feedback (ablation)PyMAF · Human3.6MMPJPE: 79.6 -> 76.8Improved
add dense correspondence auxiliary supervision (ablation)PyMAF · Human3.6MMPJPE: 76.8 -> 75.1Improved
use dense correspondence instead of part segmentation as supervision (ablation)PyMAF · Human3.6MMPJPE: 75.5 -> 75.1Improved
feed auxiliary predictions rather than features to regressor (ablation)PyMAF · Human3.6MMPJPE: 75.1 -> 77.8Hurt
add spatial alignment attention (ablation)PyMAF · Human3.6MMPJPE: 76.8 -> 73.6Improved
add grid features by fully-connected fusion instead of SAA (ablation)PyMAF · Human3.6MMPJPE: 76.8 -> 76.6No clear effect
add spatial alignment attention across refinement iterations (ablation)PyMAF · Human3.6MMPJPE: 75.1 -> 72.1Improved
use adaptive integration instead of learned integration (ablation)PyMAF-X · EHFhand MPJPE: 42.3 -> 31.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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