Reproduce “RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation” 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
Yuhan Li, Xianfeng Tan, Fangao Zeng, Wenxiang Shang, Pipei Huang, Hao Zhou, Zhiyu Jin, Wenjun Zhang and 1 more
RAGDiffusion++ restores worn-garment photos as forward-facing flat-lays, combining retrieval-based shape guidance with reward-guided generation that favors garment details and penalizes artificial patterns. On the 1,969-pair STGarment-Plus test set, using 25-step sampling, it reports FID 8.564 versus 9.990 for RAGDiffusion. This full-system comparison does not isolate reinforcement learning, and RAGDiffusion++ is not better on every dataset split.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.