Mapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping
This work addresses the problem of generating multiple high-resolution outputs from low-resolution inputs for computer vision applications, but it is incremental as it builds on existing non-adversarial mapping techniques.
The paper tackles the single image super-resolution (SISR) problem by framing it as a one-to-many mapping challenge and proposes SR-NAM with a learned degradation model to generate realistic low-resolution images, achieving qualitative improvements over methods that use simple down-sampling.
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.