Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling

arXiv:2305.16965v2 Announce Type: replace-cross
Abstract: Diffusion models have recently demonstrated an impressive ability to address inverse problems in an unsupervised manner. While existing methods primarily focus on modifying the posterior sampling process, the potential of the forward process remains largely unexplored. In this work, we propose Shortcut Sampling for Diffusion(SSD), a novel approach for solving inverse problems in a zero-shot manner. Instead of initiating from random noise, the core concept of SSD is to find a specific transitional state that …

arxiv cs.cv cs.lg diffusion diffusion models eess.iv sampling shortcut through type