Author name: Letian Wang, Andrei Zanfir, Eduard Gabriel Bazavan, Misha Andriluka, Cristian Sminchisescu

arXiv:2603.25892v1 Announce Type: new
Abstract: We present THFM, a unified video foundation model for human-centric perception that jointly addresses dense tasks (depth, normals, segmentation, dense pose) and sparse tasks (2d/3d keypoint estimation) w…