Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models 事件

Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models arXiv:2605.31162v1 Announce Type: new Abstract: Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching, the dominant paradigm for training-free diffusion editing, systematically fails for global, low-level transformations required for aesthetic and perceptual refinement. We introduce a novel, gener