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

翻译：扩散模型近期在无监督方式下解决逆问题方面展现出令人瞩目的能力。现有方法主要聚焦于修改后验采样过程，而正向过程的潜力尚未得到充分探索。本文提出一种名为"面向扩散的快捷采样"（SSD）的新方法，用于以零样本方式解决逆问题。SSD的核心思想并非从随机噪声出发，而是寻找一个能够桥接测量图像y与恢复图像x的特定过渡状态。通过利用"输入-过渡状态-输出"的快捷路径，SSD能够在更少的步骤中实现精确恢复。为在正向过程中推导过渡状态，我们引入了失真自适应反演算法。此外，我们在生成过程中采用反向投影作为额外的约束条件。实验表明，SSD在多个代表性逆问题任务上均具有有效性。与最先进的零样本方法（100次神经函数评估）相比，本方法仅需30次神经函数评估即可达到竞争性结果，并在某些任务中以100次神经函数评估超越前者。代码已开源至https://github.com/GongyeLiu/SSD