3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training

arXiv:2106.04274v4 Announce Type: replace
Abstract: 3D human pose estimation from a single image is still a challenging problem despite the large amount of work that has been performed in this field. Generally, most methods directly use neural networks and ignore certain constraints (e.g., reprojection constraints, joint angle, and bone length constraints). While a few methods consider these constraints but train the network separately, they cannot effectively solve the depth ambiguity problem. In this paper, we propose a GAN-based model for …

abstract adversarial adversarial training arxiv constraints cs.cv human image networks neural networks training type work