SOURCE-LINKED INTELLIGENCE

RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation

arXiv · AI, language, vision and robotics · article · Aug 29, 2026 · UTC

Standard clothing asset generation---restoring forward-facing flat-lay garment images from diverse real-world contexts---holds immense commercial value yet demands both macroscopic topological accuracy and microscopic physical fidelity. Although our previous work RAGDiffusion effectively eradicated large-scale structural hallucinations via retrieval-augmented macro-constraints, achieving industrial-grade micro-texture realism remains an unsolved bottleneck. We formally identify this limitation as High-Frequency Trajectory Collapse: supervised fine-tuning (SFT) converges to the conditional mean

Read original source ↗ Open in workspace

recordType

paper

region

Global