Reproduce “NV-Generate-Body: 3D Latent Diffusion Model forControllable Anatomy, Tumor, and Demographic Body Mask Synthesis” 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

Can Zhao, Pengfei Guo, Dong Yang, Yufan He, Yucheng Tang, Ahmed Harouni, Benjamin Simon, Mason Belue and 3 more

NV-Generate-Body generates 3D CT segmentation masks directly, with controls for organ sizes, tumor burdens, and demographics. The model uses latent-space 3D diffusion, tumor injection, and a size-adaptive ROI loss. At CFG 2, spleen-size rank correlation rises from 0.49 in v1 to 0.80 in v2; this measures control alignment, not clinical utility or downstream gains.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.