Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in real-world, due to the domain gap between the artificially synthesized and real LR images. Some efforts are thus taken to capture real-world image pairs. However, the captured LR-HR image pairs usually suffer from unavoidable misalignment, which hampers the performance of end- to-end learning. Here, focusing on the real-world SR, we ask a different question: since misalignment is unavoidable, can we propose a method that does not need LR-HR image pairing and alignment at all and utilizes real images as they are? Hence we propose a framework to learn SR from an arbitrary set of unpaired LR and HR images and see how far a step can go in such a realistic and “unsupervised” setting. To do so, we firstly train a degradation generation network to generate realistic LR images and, more importantly, to capture their distribution (i.e., learning to zoom out). Instead of assuming the domain gap has been eliminated, we minimize the discrepancy between the generated data and real data while learning a degradation adaptive SR network (i.e., learning to zoom in). The proposed unpaired method achieves state-of- the-art SR results on real-world images, even in the datasets that favour the paired-learning methods more.

中文翻译：

---

通过学习缩小来学习放大：通过生成和适应退化来实现现实世界的超分辨率


大多数基于学习的超分辨率（SR）方法旨在通过学习 LR-HR 图像对从给定的低分辨率（LR）图像中恢复高分辨率（HR）图像。由于人工合成图像和真实 LR 图像之间存在域差距，在合成数据上学习的 SR 方法在现实世界中表现不佳。因此，需要付出一些努力来捕捉真实世界的图像对。然而，捕获的 LR-HR 图像对通常会出现不可避免的错位，这会影响端到端学习的性能。在这里，着眼于现实世界的SR，我们提出一个不同的问题：由于失准是不可避免的，我们能否提出一种根本不需要LR-HR图像配对和对齐并直接利用真实图像的方法？因此，我们提出了一个框架，可以从任意一组未配对的 LR 和 HR 图像中学习 SR，并看看在这种现实且“无监督”的环境中，一步可以走多远。为此，我们首先训练退化生成网络来生成逼真的 LR 图像，更重要的是，捕获它们的分布（即学习缩小）。我们没有假设域间隙已被消除，而是在学习退化自适应 SR 网络（即学习放大）时最小化生成的数据与真实数据之间的差异。所提出的未配对方法在现实世界图像上实现了最先进的 SR 结果，即使在更倾向于配对学习方法的数据集中也是如此。