Reproduce “Deformable Texture Maps: Compiling Dynamic Microgeometry into Neural Textures” 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
Antonio Arian Silaghi, Zhen Chen, Danny Kaufman, Élie Michel, Jean-Marc Thiery, Jorge Lopez-Moreno, Elena Garces
The authors introduce Deformable Texture Maps (DTM), which predict yarn maps from coarse cloth’s local stretch and shear. Trained on deformed yarn configurations, the maps encode coverage, orientation, depth, and material identity, allowing conventional shading and cached reuse instead of rendering yarn geometry each frame. In a 1920 × 1080 benchmark, caching averaged 969.8 FPS versus 459.6. The results cover five yarn structures, not cloth generally.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.