1 video encoder with a query-based predictor.
One video model jointly tracks 3D hands and camera motion
V-JEPA Hand reconstructs bilateral hand trajectories and camera movement from egocentric clips in one feed-forward pass.
Big Tech
Ruicheng Li · Qixiu Li · Yu Deng · Sicheng Xu · Jiaolong Yang · Baining Guo
Tsinghua University · Microsoft Research
Research Digest··2 min read
Li and colleagues present a video model that jointly estimates hand pose, hand visibility, camera motion and, when needed, focal length from first-person footage.
§