The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimation

1 May 2022  ·  Zhe Wang, Jimei Yang, Charless Fowlkes ·

Nonparametric based methods have recently shown promising results in reconstructing human bodies from monocular images while model-based methods can help correct these estimates and improve prediction. However, estimating model parameters from global image features may lead to noticeable misalignment between the estimated meshes and image evidence. To address this issue and leverage the best of both worlds, we propose a framework of three consecutive modules. A dense map prediction module explicitly establishes the dense UV correspondence between the image evidence and each part of the body model. The inverse kinematics module refines the key point prediction and generates a posed template mesh. Finally, a UV inpainting module relies on the corresponding feature, prediction and the posed template, and completes the predictions of occluded body shape. Our framework leverages the best of non-parametric and model-based methods and is also robust to partial occlusion. Experiments demonstrate that our framework outperforms existing 3D human estimation methods on multiple public benchmarks.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Absolute Human Pose Estimation Human3.6M MBNA PA-MPJPE 38.4 # 1
3D Human Pose Estimation Human3.6M MBNA Average MPJPE (mm) 54.7 # 216

Methods