A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation

arXiv:2403.11310v1 Announce Type: new
Abstract: 3D human pose data collected in controlled laboratory settings present challenges for pose estimators that generalize across diverse scenarios. To address this, domain generalization is employed. Current methodologies in domain generalization for 3D human pose estimation typically utilize adversarial training to generate synthetic poses for training. Nonetheless, these approaches exhibit several limitations. First, the lack of prior information about the target domain complicates the application of suitable augmentation through a single pose augmentor, affecting generalization …

abstract adversarial adversarial training arxiv challenges cs.cv current data diverse domain framework generate human laboratory synthetic training type