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

by   Vasileios Lioutas, et al.

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.


page 3

page 5

page 6

page 7

page 8

page 9


A Generative Model for Hallucinating Diverse Versions of Super Resolution Images

Traditionally, the main focus of image super-resolution techniques is on...

Creating High Resolution Images with a Latent Adversarial Generator

Generating realistic images is difficult, and many formulations for this...

Learning a Mixture of Deep Networks for Single Image Super-Resolution

Single image super-resolution (SR) is an ill-posed problem which aims to...

Image Matching with Scale Adjustment

In this paper we address the problem of matching two images with two dif...

Breathing deformation model – application to multi-resolution abdominal MRI

Dynamic MRI is a technique of acquiring a series of images continuously ...

Resolution enhancement of placenta histological images using deep learning

In this study, a method has been developed to improve the resolution of ...

Super-resolving Dark Matter Halos using Generative Deep Learning

Generative deep learning methods built upon Convolutional Neural Network...

Please sign up or login with your details

Forgot password? Click here to reset