ResShift：通过残差平移实现图像超分辨率的高效扩散模型
ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting
AI总结：
针对扩散模型图像超分辨率推理慢且加速采样牺牲性能的问题，提出ResShift模型，通过构建马尔可夫链平移高低分辨率图像残差并设计精细噪声调度，仅需15步即可达到SOTA性能。
摘要：
基于扩散的图像超分辨率（SR）方法主要受限于较低的推理速度，因为需要数百甚至数千个采样步骤。现有的加速采样技术不可避免地会在一定程度上牺牲性能，导致过度模糊的SR结果。为了解决这个问题，我们提出了一种新颖且高效的SR扩散模型，该模型显著减少了扩散步骤的数量，从而消除了推理过程中对后加速的需求及其相关的性能下降。我们的方法构建了一个马尔可夫链，通过平移高分辨率图像和低分辨率图像之间的残差来实现两者之间的转换，从而大幅提高了转换效率。此外，还开发了一种精细的噪声调度方案，以灵活控制扩散过程中的平移速度和噪声强度。大量实验表明，所提出的方法在合成和真实世界数据集上均获得了优于或至少与当前最先进方法相当的性能，即使仅使用15个采样步骤。我们的代码和模型可在 https://github.com/zsyOAOA/ResShift 获取。
英文摘要：
Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice performance to some extent, leading to over-blurry SR results. To address this issue, we propose a novel and efficient diffusion model for SR that significantly reduces the number of diffusion steps, thereby eliminating the need for post-acceleration during inference and its associated performance deterioration. Our method constructs a Markov chain that transfers between the high-resolution image and the low-resolution image by shifting the residual between them, substantially improving the transition efficiency. Additionally, an elaborate noise schedule is developed to flexibly control the shifting speed and the noise strength during the diffusion process. Extensive experiments demonstrate that the proposed method obtains superior or at least comparable performance to current state-of-the-art methods on both synthetic and real-world datasets, even only with 15 sampling steps. Our code and model are available at https://github.com/zsyOAOA/ResShift.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
