Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details. In this paper, we propose a novel BSR approach, Content-aware Degradation-driven Transformer (CDFormer), to capture both degradation and content representations. However, low-resolution images cannot provide enough content details, and thus we introduce a diffusion-based module $CDFormer_{diff}$ to first learn Content Degradation Prior (CDP) in both low- and high-resolution images, and then approximate the real distribution given only low-resolution information. Moreover, we apply an adaptive SR network $CDFormer_{SR}$ that effectively utilizes CDP to refine features. Compared to previous diffusion-based SR methods, we treat the diffusion model as an estimator that can overcome the limitations of expensive sampling time and excessive diversity. Experiments show that CDFormer can outperform existing methods, establishing a new state-of-the-art performance on various benchmarks under blind settings. Codes and models will be available at \href{https://github.com/I2-Multimedia-Lab/CDFormer}{https://github.com/I2-Multimedia-Lab/CDFormer}.

翻译：现有的盲图像超分辨率（BSR）方法主要关注估计核或退化信息，但长期忽视了关键的内容细节。本文提出一种新颖的BSR方法——内容感知退化驱动Transformer（CDFormer），以同时捕捉退化与内容表示。然而，低分辨率图像无法提供足够的内容细节，因此我们引入基于扩散的模块$CDFormer_{diff}$，先同时学习低分辨率和高分辨率图像中的内容退化先验（CDP），再仅利用低分辨率信息近似真实分布。此外，我们应用自适应超分辨率网络$CDFormer_{SR}$，有效利用CDP来细化特征。与先前基于扩散的SR方法相比，我们将扩散模型视为估计器，从而克服采样时间长、多样性过高的局限。实验表明，CDFormer能够超越现有方法，在多种盲设置基准上树立新的最先进性能。代码与模型将发布在\href{https://github.com/I2-Multimedia-Lab/CDFormer}{https://github.com/I2-Multimedia-Lab/CDFormer}。