论文标题
SIMUSR：无监督图像超分辨率的简单但强大的基线
SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution
论文作者
论文摘要
在本文中，我们解决了一个完全无监督的超分辨率问题，即既不是配对的图像也不是真实的HR图像。我们假设与高分辨率（HR）图像相比，低分辨率（LR）图像相对容易收集。通过允许多个LR图像，我们通过降采样的LR图像并将原始的无监督问题投入到一个有监督的学习问题中，但在一个级别较低的层面上构建了一组伪对。尽管这一研究很容易考虑，因此应该在任何复杂的无监督方法之前进行调查，但令人惊讶的是，目前没有。更重要的是，我们表明，这种简单的方法的表现优于最先进的无监督方法，其运行时的延迟较短，并且大大缩小了对HR监督模型的差距。我们在NTIRE 2020超分辨率挑战赛中提交了我们的方法，并在PSNR中获得了第一名，在SSIM中获得了第2名，在LPIP中获得了第13位。这种简单的方法应作为将来击败的基线，尤其是在训练阶段允许多个LR图像时。但是，即使在零拍摄的条件下，我们也认为该方法可以作为有用的基线，以查看受监督和无监督框架之间的差距。
In this paper, we tackle a fully unsupervised super-resolution problem, i.e., neither paired images nor ground truth HR images. We assume that low resolution (LR) images are relatively easy to collect compared to high resolution (HR) images. By allowing multiple LR images, we build a set of pseudo pairs by denoising and downsampling LR images and cast the original unsupervised problem into a supervised learning problem but in one level lower. Though this line of study is easy to think of and thus should have been investigated prior to any complicated unsupervised methods, surprisingly, there are currently none. Even more, we show that this simple method outperforms the state-of-the-art unsupervised method with a dramatically shorter latency at runtime, and significantly reduces the gap to the HR supervised models. We submitted our method in NTIRE 2020 super-resolution challenge and won 1st in PSNR, 2nd in SSIM, and 13th in LPIPS. This simple method should be used as the baseline to beat in the future, especially when multiple LR images are allowed during the training phase. However, even in the zero-shot condition, we argue that this method can serve as a useful baseline to see the gap between supervised and unsupervised frameworks.
