Reproduce “Scalable DDPM-Polycube: An Extended Diffusion-Based Method for Hexahedral Mesh and Volumetric Spline Construction” 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
Yuxuan Yu, Jiashuo Liu, Hua Tong, Honghua Lou, Yongjie Jessica Zhang
SDDPM maps CAD surfaces to polycube parameter spaces for isogeometric analysis (IGA), using diffusion conditioned on cell-wise primitive labels. It adds a blind-hole cube (BHC) primitive and hierarchical context checks to represent features not distinguished by global genus. In a controlled genus-0 Spline Link example, BHC+Z reduced average Chamfer distance from 0.2785 to 0.0292; this is a single-case result.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.