RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation
This work formally identifies this limitation as High-Frequency Trajectory Collapse: supervised fine-tuning converges to the conditional mean of the training distribution, which is dominated by smooth, low-frequency textures, causing high-frequency patterns to become nearly un-sampleable.
Yuhan Li, Xianfeng Tan, Fan-Gao Zeng et al.
· 0 citations