PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images

13 Jul 2022  ·  Hongwen Zhang, Yating Tian, Yuxiang Zhang, Mengcheng Li, Liang An, Zhenan Sun, Yebin Liu ·

We present PyMAF-X, a regression-based approach to recovering parametric full-body models from monocular images. This task is very challenging since minor parametric deviation may lead to noticeable misalignment between the estimated mesh and the input image. Moreover, when integrating part-specific estimations into the full-body model, existing solutions tend to either degrade the alignment or produce unnatural wrist poses. To address these issues, we propose a Pyramidal Mesh Alignment Feedback (PyMAF) loop in our regression network for well-aligned human mesh recovery and extend it as PyMAF-X for the recovery of expressive full-body models. The core idea of PyMAF is to leverage a feature pyramid and rectify the predicted parameters explicitly based on the mesh-image alignment status. Specifically, given the currently predicted parameters, mesh-aligned evidence will be extracted from finer-resolution features accordingly and fed back for parameter rectification. To enhance the alignment perception, an auxiliary dense supervision is employed to provide mesh-image correspondence guidance while spatial alignment attention is introduced to enable the awareness of the global contexts for our network. When extending PyMAF for full-body mesh recovery, an adaptive integration strategy is proposed in PyMAF-X to produce natural wrist poses while maintaining the well-aligned performance of the part-specific estimations. The efficacy of our approach is validated on several benchmark datasets for body, hand, face, and full-body mesh recovery, where PyMAF and PyMAF-X effectively improve the mesh-image alignment and achieve new state-of-the-art results. The project page with code and video results can be found at https://www.liuyebin.com/pymaf-x.

PDF Abstract

Results from the Paper


Ranked #6 on 3D Human Pose Estimation on AGORA (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
3D Human Pose Estimation 3DPW PyMAF-X PA-MPJPE 45.3 # 36
MPJPE 74.2 # 34
MPVPE 87.0 # 30
3D Human Pose Estimation AGORA PyMAF-X B-NMVE 94.4 # 6
B-NMJE 93.5 # 6
B-MVE 84.0 # 6
B-MPJPE 83.2 # 5
3D Human Pose Estimation Human3.6M PyMAF (HR48) Average MPJPE (mm) 54.2 # 211
PA-MPJPE 37.2 # 34

Methods


No methods listed for this paper. Add relevant methods here