arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.03444eess.IVcs.CV
收藏

通过自适应下采样模型实现真实世界的超分辨率

Toward Real-World Super-Resolution via Adaptive Downsampling Models

Seoul National University(首尔大学);Google(谷歌);UC Merced(加州大学默塞德分校);Yonsei University(延世大学)

Sanghyun Son, Jaeha Kim, Wei-Sheng Lai, Ming-Husan Yang, Kyoung Mu Lee

摘要:

大多数图像超分辨率(SR)方法是在通过预定操作构建的合成低分辨率(LR)和高分辨率(HR)图像对上开发的,例如,双三次下采样由于现有的方法通常学习特定函数的逆映射,因此当应用于真实世界的图像时,它们会产生模糊的结果,这些图像的确切公式是不同的和未知的。因此,有几种方法试图合成更多样化的LR样本或学习实际的下采样模型。然而,由于对下采样过程的限制性假设,它们仍然是有偏差的,不太普遍。本研究提出一种新的方法来模拟一个未知的下采样过程,而不施加限制性的先验知识。我们在对抗训练框架中提出了一个可推广的低频损失(LFL)来模仿目标LR图像的分布,而不使用任何配对的例子。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。大量的实验验证了我们的下采样模型可以帮助现有的SR方法在各种合成和真实世界的例子上执行比传统方法更准确的重建。

英文摘要:

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.

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。

↑