Papers › Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling

26 May 2023arXiv:2305.16965archive 2025-07-28

Gongye Liu, Haoze Sun, Jiayi Li, Fei Yin, Yujiu Yang

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 bridges the measurement image y and the restored image x. By utilizing the shortcut path of "input - transitional state - output", SSD can achieve precise restoration with fewer steps. To derive the transitional state during the forward process, we introduce Distortion Adaptive Inversion. Moreover, we apply back projection as additional consistency constraints during the generation process. Experimentally, we demonstrate SSD's effectiveness on multiple representative IR tasks. Our method achieves competitive results with only 30 NFEs compared to state-of-the-art zero-shot methods(100 NFEs) and outperforms them with 100 NFEs in certain tasks. Code is available at https://github.com/GongyeLiu/SSD

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

gongyeliu/ssd officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ColorizationDeblurringSuper-Resolution

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionDiffusionFocusNon Maximum SuppressionSSD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections