通过扩散反演的任意步骤图像超分辨率

Arbitrary-steps Image Super-resolution via Diffusion Inversion

December 12, 2024

作者: Zongsheng Yue, Kang Liao, Chen Change Loy

cs.AI

摘要

本研究提出了一种基于扩散反演的新图像超分辨率（SR）技术，旨在利用大型预训练扩散模型中包含的丰富图像先验信息来提高SR性能。我们设计了一种部分噪声预测策略，用于构建扩散模型的中间状态，作为起始采样点。我们方法的核心是一个深度噪声预测器，用于估计前向扩散过程的最佳噪声图，一经训练，该噪声预测器可用于沿着扩散轨迹部分初始化采样过程，生成理想的高分辨率结果。与现有方法相比，我们的方法提供了一种灵活高效的采样机制，支持从一到五个任意数量的采样步骤。即使只有一个采样步骤，我们的方法也展示出优越或可比较的性能，超过了最近的最新方法。代码和模型可在https://github.com/zsyOAOA/InvSR 上公开获取。

English

This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise Prediction strategy to construct an intermediate state of the diffusion model, which serves as the starting sampling point. Central to our approach is a deep noise predictor to estimate the optimal noise maps for the forward diffusion process. Once trained, this noise predictor can be used to initialize the sampling process partially along the diffusion trajectory, generating the desirable high-resolution result. Compared to existing approaches, our method offers a flexible and efficient sampling mechanism that supports an arbitrary number of sampling steps, ranging from one to five. Even with a single sampling step, our method demonstrates superior or comparable performance to recent state-of-the-art approaches. The code and model are publicly available at https://github.com/zsyOAOA/InvSR.