Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment

arXiv:2404.09499v1 Announce Type: new
Abstract: Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics. Many previous methods grapple with this inherently ambiguous task by introducing motion priors into the learning process. However, these approaches face difficulties in defining the complete configurations of such priors or training a robust model. In this paper, we present the Video-to-Motion Generator (VTM), which leverages motion priors through cross-modal latent feature space alignment between …

abstract alignment arxiv computer computer graphics computer vision cs.cv cs.gr face graphics however human inputs manifold modal process type via videos vision