AI Paper Atlas

Research map / 3D vision / Human pose estimation

PyMAF: 3D Human Pose and Shape Regression With Pyramidal Mesh Alignment Feedback Loop

Hongwen Zhang, Yating Tian, Xinchi Zhou, Wanli Ouyang, Yebin Liu, Limin Wang, Zhenan Sun

ICCV 2021 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 359 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 mesh-aligned features instead of grid features (no pyramid) (ablation)PyMAF feedback loop · Human3.6MMPJPE (mm): 80.5 -> 79.6Improved
use mesh-aligned instead of grid features with pyramid (ablation)PyMAF · Human3.6MMPJPE (mm): 79.7 -> 76.8Improved
use grid instead of global features (ablation)feedback loop · Human3.6MMPJPE (mm): 84.3 -> 80.5Improved
add feature pyramid and 3 regressors to mesh-aligned feedback (ablation)PyMAF · Human3.6MMPJPE (mm): 79.6 -> 76.8Improved
add auxiliary dense correspondence supervision (ablation)PyMAF · Human3.6MMPJPE (mm): 76.8 -> 75.1Improved
add auxiliary part segmentation supervision (ablation)PyMAF · Human3.6MMPJPE (mm): 76.8 -> 75.5Improved
use dense correspondences instead of part segmentation for auxiliary supervision (ablation)PyMAF · Human3.6MMPJPE (mm): 75.5 -> 75.1Improved
use feature maps instead of auxiliary predictions as regressor input (ablation)PyMAF · Human3.6MMPJPE (mm): 77.8 -> 75.1Improved
mask mesh-aligned features with foreground part segmentation (ablation)PyMAF · Human3.6MMPJPE (mm): 75.5 -> 77.6Hurt
add auxiliary supervision (ablation)PyMAF · 3DPWMPJPE (mm): 95.6 -> 92.8Improved
add auxiliary supervision (ablation)PyMAF · Human3.6MMPJPE (mm): 60.3 -> 57.7Improved
add auxiliary supervision (ablation)PyMAF · 3DPWPA-MPJPE (mm): 58.8 -> 58.9No clear effect

Later papers that compared with this method

1 later accepted paper reports PyMAF * as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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