WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

arXiv:2312.07531v2 Announce Type: replace
Abstract: The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating humans in global coordinates often assumes a flat ground plane and produces foot sliding. Third, the most accurate methods rely on computationally expensive optimization pipelines, limiting their use to offline applications. Finally, existing video-based methods are surprisingly less accurate than single-frame methods. …

arxiv cs.cv humans type world