Blind image super-resolution (Blind-SR) aims to recover a high-resolution (HR) image from its corresponding low-resolution (LR) input image with unknown degradations. Most of the existing works design an explicit degradation estimator for each degradation to guide SR. However, it is infeasible to provide concrete labels of multiple degradation combinations (e.g., blur, noise, jpeg compression) to supervise the degradation estimator training. In addition, these special designs for certain degradation, such as blur, impedes the models from being generalized to handle different degradations. To this end, it is necessary to design an implicit degradation estimator that can extract discriminative degradation representation for all degradations without relying on the supervision of degradation ground-truth. In this paper, we propose a Knowledge Distillation based Blind-SR network (KDSR). It consists of a knowledge distillation based implicit degradation estimator network (KD-IDE) and an efficient SR network. To learn the KDSR model, we first train a teacher network: KD-IDE$_{T}$. It takes paired HR and LR patches as inputs and is optimized with the SR network jointly. Then, we further train a student network KD-IDE$_{S}$, which only takes LR images as input and learns to extract the same implicit degradation representation (IDR) as KD-IDE$_{T}$. In addition, to fully use extracted IDR, we design a simple, strong, and efficient IDR based dynamic convolution residual block (IDR-DCRB) to build an SR network. We conduct extensive experiments under classic and real-world degradation settings. The results show that KDSR achieves SOTA performance and can generalize to various degradation processes. The source codes and pre-trained models will be released.

翻译：盲图像超分辨率旨在从带有未知退化的低分辨率输入图像中恢复高分辨率图像。现有方法大多针对每种退化设计显式退化估计器以引导超分辨率重建，但为多种退化组合（如模糊、噪声、JPEG压缩）提供具体标签以监督退化估计器训练并不可行。此外，针对特定退化（如模糊）的特殊设计阻碍了模型泛化处理不同退化场景。因此，有必要设计一种无需退化真值监督、能提取所有退化类型的判别性退化表征的隐式退化估计器。本文提出基于知识蒸馏的盲超分辨率网络KDSR，包含基于知识蒸馏的隐式退化估计网络KD-IDE与高效超分辨率网络。为训练KDSR模型，首先训练教师网络KD-IDE$_{T}$，该网络以配对的HR与LR图像块为输入，并与超分辨率网络联合优化；随后训练学生网络KD-IDE$_{S}$，仅以LR图像为输入，学习提取与KD-IDE$_{T}$相同的隐式退化表征IDR。为充分利用提取的IDR，进一步设计基于IDR的简单、强健且高效的动态卷积残差块IDR-DCRB以构建超分辨率网络。在经典退化与真实退化场景下开展的大量实验表明，KDSR达到最优性能，并能泛化处理多种退化过程。源代码与预训练模型将开源。