Fast and Accurate Hand Estimation in Pixels, Interaction and World Space
Read the original on arXiv Computer Vision →Fast and Accurate Hand Estimation (FAH) is a new family of monocular hand mesh estimators that directly predict 3D joints and surface points, then fit a mesh model such as MANO or MHR-Hand. Built on SAM 3D Body’s hand branch, FAH uses fine‑tuning and feature distillation to produce accurate 2D and 3D keypoints, optional anatomical part segmentation, and contact estimation without requiring object geometry. The models achieve state‑of‑the‑art image‑space alignment, hand geometry, contact estimation, and world‑space tracking, running at 65 fps (ViT‑L) or 125 fps (ViT‑S) on an RTX 4070 Ti SUPER.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.