Reproduce “GNM Head: A Generative aNthropometric Model of the human head” 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
Stylianos Ploumpis, Jan Bednarik, Gaspard Zoss, Ruslan Guseinov, Luca Prasso, Prashanth Chandran, Oliver Boyne, Vasileios Choutas and 24 more
GNM fits controllable 3D head models to images using explicit teeth, tongue, and eye structures with regional expression controls. An in-the-wild example shows a tongue-bearing head mesh fitted from an image and detected landmarks. On 15,000 held-out scans, mean scan-to-mesh distance is 0.748 mm, versus 0.971 mm for FLAME, over a facial region; the comparison does not isolate anatomy’s effect.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.