Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. Conventional SR methods typically gather the paired training data by synthesizing LR images from HR images using a predetermined degradation model, e.g., Bicubic down-sampling. However, the realistic degradation type of test images may mismatch with the training-time degradation type due to the dynamic changes of the real-world scenarios, resulting in inferior-quality SR images. To address this, existing methods attempt to estimate the degradation model and train an image-specific model, which, however, is quite time-consuming and impracticable to handle rapidly changing domain shifts. Moreover, these methods largely concentrate on the estimation of one degradation type (e.g., blur degradation), overlooking other degradation types like noise and JPEG in real-world test-time scenarios, thus limiting their practicality. To tackle these problems, we present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types. Specifically, we design a second-order degradation scheme to construct paired data based on the degradation type of the test image, which is predicted by a pre-trained degradation classifier. Then, we adapt the SR model by implementing feature-level reconstruction learning from the initial test image to its second-order degraded counterparts, which helps the SR model generate plausible HR images. Extensive experiments are conducted on newly synthesized corrupted DIV2K datasets with 8 different degradations and several real-world datasets, demonstrating that our SRTTA framework achieves an impressive improvement over existing methods with satisfying speed. The source code is available at https://github.com/DengZeshuai/SRTTA.

翻译：图像超分辨率（SR）旨在利用配对的低分辨率（LR）与高分辨率（HR）训练图像，学习从LR到HR的映射。传统SR方法通常通过预设退化模型（如双三次下采样）从HR图像合成LR图像来获取配对训练数据。然而，由于真实场景的动态变化，测试图像的退化类型可能与训练时的退化类型不匹配，导致SR图像质量下降。为解决这一问题，现有方法尝试估计退化模型并训练图像专属模型，但此过程相当耗时，且难以应对快速变化的领域偏移。此外，这些方法主要集中于单一退化类型（如模糊退化）的估计，忽视了真实测试场景中存在的噪声、JPEG等其他退化类型，从而限制了其实用性。针对上述问题，我们提出了一种高效的测试时自适应SR框架（SRTTA），该框架能够快速将SR模型适配至具有不同/未知退化类型的测试领域。具体而言，我们设计了一个二阶退化方案，基于预训练退化分类器预测的测试图像退化类型来构建配对数据。随后，通过从初始测试图像到其二阶退化对应图像的特征级重建学习来适配SR模型，这有助于SR模型生成更合理的HR图像。我们在新合成的包含8种不同退化的损坏DIV2K数据集以及多个真实世界数据集上进行了大量实验，结果表明SRTTA框架在保证满意速度的同时，相较于现有方法实现了显著性能提升。源代码已开源：https://github.com/DengZeshuai/SRTTA。