Reproduce “VACO: Vertex-Aligned Decoding for Dense Hand Contact Estimation from a Single Image” 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
Binhong Ye, Jin-Chuan Shi, Tao Liu, Xin Wang, Hao Chen, Chunhua Shen
VACO predicts dense hand contact from an RGB image by projecting MANO mesh vertices into image features and estimating contact per vertex. This mesh-aligned sampling replaces HACO’s shared contact query; a co-trained reconstruction backbone supplies the projections. On Hi4D, VACO reports F1 0.860 versus HACO’s 0.653, an in-domain, single-run result that does not establish localization as the sole cause.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.