Reproduce “DenseHap: Dense Hand Haptic Estimation from Monocular Images” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Junhan Xue, Rolandos Alexandros Potamias
DenseHap predicts contact, distance, and pressure on points of a reconstructed hand surface from one image. It uses shared image features and hand geometry, with per-vertex queries attending to image patches, to produce the outputs in one forward pass. On held-out ContactPose, contact F1 is .673 versus HACO’s .588 at the default threshold, in a zero-shot Skip-protocol evaluation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.