arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.11708eess.IVcs.CVcs.LGstat.ML
收藏

使用非对抗映射将低分辨率图像映射到多个高分辨率图像

Mapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping

Carleton University(卡尔顿大学)

Vasileios Lioutas

摘要:

最近已经提出了几种方法用于单图像超分辨率(SISR)问题。目前的方法假设一幅低分辨率图像只能产生一幅高分辨率图像。此外,所有这些方法都使用通过简单的双线性下采样人工生成的低分辨率图像。我们认为,首先,SISR的问题是低分辨率和所有可能的候选高分辨率图像之间的一对多映射问题,我们解决了学习如何现实地降低和下采样高分辨率图像的挑战性任务。为了解决这个问题,我们提出了SR-NAM,它利用了非对抗映射(NAM)技术。此外,我们提出了一个退化模型,学习如何将高分辨率图像转换为类似于现实拍摄的低分辨率照片的低分辨率图像。最后,一些定性的结果所提出的方法以及SR-NAM的弱点。

英文摘要:

Several methods have recently been proposed for the Single Image Super-Resolution (SISR) problem. The current methods assume that a single low-resolution image can only yield a single high-resolution image. In addition, all of these methods use low-resolution images that were artificially generated through simple bilinear down-sampling. We argue that, first and foremost, the problem of SISR is an one-to-many mapping problem between the low-resolution and all possible candidate high-resolution images and we address the challenging task of learning how to realistically degrade and down-sample high-resolution images. To circumvent this problem, we propose SR-NAM which utilizes the Non-Adversarial Mapping (NAM) technique. Furthermore, we propose a degradation model that learns how to transform high-resolution images to low-resolution images that resemble realistically taken low-resolution photos. Finally, some qualitative results for the proposed method along with the weaknesses of SR-NAM are included.

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。

↑