Hierarchical Kinematic Human Mesh Recovery
Authors:
Preprint
Abstract
We consider the problem of estimating a parametric model of 3D human mesh from a single image. While there has been substantial recent progress in this area with direct regression of model parameters, these methods only implicitly exploit the human body kinematic structure, leading to sub-optimal use of the model prior. In this work, we address this gap by proposing a new technique for regression of human parametric model that is explicitly informed by the known hierarchical structure, including joint interdependencies of the model. This results in a strong prior-informed design of the regressor architecture and an associated hierarchical optimization that is flexible to be used in conjunction with the current standard frameworks for 3D human mesh recovery. We demonstrate these aspects by means of extensive experiments on standard benchmark datasets, showing how our proposed new design outperforms several existing and popular methods, establishing new state-of-the-art results. By considering joint interdependencies, our method is equipped to infer joints even under data corruptions, which we demonstrate by conducting experiments under varying degrees of occlusion.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- BodyNet: Volumetric Inference of 3D Human Body Shapes2018
- Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation2018
- Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision2017
- DARWIN: Deformable Patient Avatar Representation With Deep Image Network2017
- Deep Kinematic Pose Regression2016
- Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image2016
- Convolutional Pose Machines2016
- DeepPose: Human Pose Estimation via Deep Neural Networks2014
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis2014
- Microsoft COCO: Common Objects in Context2014