Reproduce “Forwardrobe: Garment-Aware Gaussian Avatars from a Single Image” 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
Daisheng Jin, Shuyun Wang, Ying He
Forwardrobe turns a single image into an animatable, editable garment asset by separating clothing from a reconstructed 3D Gaussian avatar. For skirt-like garments, it closes the leg-shaped seam and reassigns skinning weights, then predicts motion-conditioned residuals. On NeuMan’s masked garment region, Forwardrobe (500M) reports PSNR 15.12 versus DynaAvatar’s 12.79, an improvement limited to this comparison.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.