Reproduce “Efficient Globally Optimal 2D-to-3D Deformable Shape Matching” 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
Zorah Lähner, Emanuele Rodolà, Frank R. Schmidt, Michael M. Bronstein, Daniel Cremers
The method maps a closed planar sketch to a continuous curve on a deformable 3D surface, using its matching energy to rank candidate shapes. It combines cross-modal feature similarity with a length penalty and enforces mesh connectivity through product-graph path search. On the extended dataset, the global method achieves MAP 0.9984; this does not guarantee semantic correctness beyond the tested setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.