arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.10747eess.IVcs.CVcs.LG
收藏

学习多概率退化生成器实现无监督真实世界图像超分辨率

Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution

Soongsil University(崇实大学);SI Analytics(SI分析公司)

Sangyun Lee, Sewoong Ahn, Kwangjin Yoon

摘要:

无监督真实世界超分辨率(USR)的目标是在低分辨率(LR)输入下恢复高分辨率(HR)图像,其困难在于缺乏配对数据集。最常见的方法之一是使用GANs(即,退化生成器)以及利用合成数据集以监督的方式训练模型。虽然训练退化生成器的目标是在给定HR图像的情况下近似LR图像的分布,但以前的工作严重依赖于条件分布是δ函数的不切实际的假设,并学习了从HR图像到LR图像的确定性映射。在本文中,我们表明,我们可以改善的USR模型的性能,通过放松的假设,并建议训练的概率退化发生器。我们的概率退化生成器可以被看作是一个深层次的潜变量模型,更适合于复杂的条件分布建模。我们还揭示了与StyleGAN的噪声注入的显着联系。此外,我们训练多个退化发生器,以提高模式覆盖率和应用协同学习,以方便培训。我们在PSNR和SSIM方面优于基准数据集的几个基线,并证明了我们的方法对未知数据分布的鲁棒性。代码可在https://github.com/sangyun884/MSSR上获得。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑