论文标题
学习多种概率退化发生器，用于无监督的现实世界形象超级分辨率
Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution
论文作者
论文摘要
无监督的现实世界超级分辨率（USR）旨在恢复给定低分辨率（LR）输入的高分辨率（HR）图像，其难度是由于缺乏配对数据集而造成的。最常见的方法之一是使用gans（即降解发生器）合成嘈杂的LR图像，并利用合成数据集以监督的方式训练模型。尽管训练降解发生器的目的是近似于给定HR图像的LR图像的分布，但以前的工作严重依赖于条件分布是Delta函数的不现实假设，并了解了从HR图像到LR图像的确定性映射。在本文中，我们表明我们可以通过放松假设并提议训练概率降解发生器来提高USR模型的性能。我们的概率降解发生器可以看作是深层层次潜在变量模型，并且更适合对复杂的条件分布进行建模。我们还揭示了与StyleGan的噪声注入的显着联系。此外，我们训练多个降级发生器以改善模式覆盖范围并应用协作学习以易于培训。根据PSNR和SSIM，我们在基准数据集上的表现优于几个基准，并证明了我们方法在看不见的数据分布方面的鲁棒性。代码可在https://github.com/sangyun884/mssr上找到。
Unsupervised real world super resolution (USR) aims to restore high-resolution (HR) images given low-resolution (LR) inputs, and its difficulty stems from the absence of paired dataset. One of the most common approaches is synthesizing noisy LR images using GANs (i.e., degradation generators) and utilizing a synthetic dataset to train the model in a supervised manner. Although the goal of training the degradation generator is to approximate the distribution of LR images given a HR image, previous works have heavily relied on the unrealistic assumption that the conditional distribution is a delta function and learned the deterministic mapping from the HR image to a LR image. In this paper, we show that we can improve the performance of USR models by relaxing the assumption and propose to train the probabilistic degradation generator. Our probabilistic degradation generator can be viewed as a deep hierarchical latent variable model and is more suitable for modeling the complex conditional distribution. We also reveal the notable connection with the noise injection of StyleGAN. Furthermore, we train multiple degradation generators to improve the mode coverage and apply collaborative learning for ease of training. We outperform several baselines on benchmark datasets in terms of PSNR and SSIM and demonstrate the robustness of our method on unseen data distribution. Code is available at https://github.com/sangyun884/MSSR.
