Reproduce “SeMo3D: Unifying 3D Generation, Editing, and Completion via Selective Modeling” 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
Xiaokun Sun, Jian Yang, Zhenyu Zhang
SeMo3D unifies 3D generation, editing, and completion by synthesizing selected regions while reusing clean context tokens. It trains on ordinary 3D assets, adding noise and denoising loss only in randomly selected regions, without paired editing or completion examples. On Omni-Comp, its image-and-text completion reaches F-score 0.468 versus 0.347 for HY3D-Omni under different conditions; the comparison does not isolate why.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.