Hierarchical Kinematic Human Mesh Recovery
arXiv:2003.04232
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.
arXiv comment17 pages, 8 figures, 5 tables, ECCV 2020
References in corpus (9)
- Auto-Encoding Variational Bayes
- DeepPose: Human Pose Estimation via Deep Neural Networks
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- Stacked Hourglass Networks for Human Pose Estimation
- How Robust is 3D Human Pose Estimation to Occlusion?
- Real-time Convolutional Networks for Depth-based Human Pose Estimation
- DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image
- RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation