Most image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs that are constructed by a predetermined operation, e.g., bicubic downsampling. As existing methods typically learn an inverse mapping of the specific function, they produce blurry results when applied to real-world images whose exact formulation is different and unknown. Therefore, several methods attempt to synthesize much more diverse LR samples or learn a realistic downsampling model. However, due to restrictive assumptions on the downsampling process, they are still biased and less generalizable. This study proposes a novel method to simulate an unknown downsampling process without imposing restrictive prior knowledge. We propose a generalizable low-frequency loss (LFL) in the adversarial training framework to imitate the distribution of target LR images without using any paired examples. Furthermore, we design an adaptive data loss (ADL) for the downsampler, which can be adaptively learned and updated from the data during the training loops. Extensive experiments validate that our downsampling model can facilitate existing SR methods to perform more accurate reconstructions on various synthetic and real-world examples than the conventional approaches.

中文翻译：

---

通过自适应下采样模型实现真实世界的超分辨率。

大多数图像超分辨率 (SR) 方法是在合成低分辨率 (LR) 和高分辨率 (HR) 图像对上开发的，这些图像对由预定操作（例如，双三次下采样）构建。由于现有方法通常学习特定函数的逆映射，因此当应用于确切公式不同且未知的真实世界图像时，它们会产生模糊的结果。因此，有几种方法试图合成更多样的 LR 样本或学习真实的下采样模型。然而，由于对下采样过程的限制性假设，它们仍然存在偏差且泛化性较差。本研究提出了一种新方法来模拟未知的下采样过程，而无需施加限制性先验知识。我们在对抗性训练框架中提出了一种可泛化的低频损失 (LFL)，以在不使用任何配对示例的情况下模仿目标 LR 图像的分布。此外，我们为下采样器设计了一个自适应数据丢失（ADL），它可以在训练循环期间从数据中自适应地学习和更新。大量实验证实，与传统方法相比，我们的下采样模型可以促进现有的 SR 方法对各种合成和真实示例进行更准确的重建。