We present a novel motion prior, called PhaseMP , modeling a probability distribution on pose transitions conditioned by a frequency domain feature extracted from a periodic autoencoder. The phase feature further enforces the pose transitions to be …
As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the …
In this paper, we introduce a set of simple yet effective TOken REduction (TORE) strategies for Transformer-based Human Mesh Recovery from monocular images. Current SOTA performance is achieved by Transformer-based structures. However, they suffer …