Log In Sign Up

To learn image super-resolution, use a GAN to learn how to do image degradation first

by   Adrian Bulat, et al.

This paper is on image and face super-resolution. The vast majority of prior work for this problem focus on how to increase the resolution of low-resolution images which are artificially generated by simple bilinear down-sampling (or in a few cases by blurring followed by down-sampling).We show that such methods fail to produce good results when applied to real-world low-resolution, low quality images. To circumvent this problem, we propose a two-stage process which firstly trains a High-to-Low Generative Adversarial Network (GAN) to learn how to degrade and downsample high-resolution images requiring, during training, only unpaired high and low-resolution images. Once this is achieved, the output of this network is used to train a Low-to-High GAN for image super-resolution using this time paired low- and high-resolution images. Our main result is that this network can be now used to efectively increase the quality of real-world low-resolution images. We have applied the proposed pipeline for the problem of face super-resolution where we report large improvement over baselines and prior work although the proposed method is potentially applicable to other object categories.


page 2

page 5

page 7

page 13

page 14


A Generative Model for Hallucinating Diverse Versions of Super Resolution Images

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

SRDGAN: learning the noise prior for Super Resolution with Dual Generative Adversarial Networks

Single Image Super Resolution (SISR) is the task of producing a high res...

Real-World Super-Resolution of Face-Images from Surveillance Cameras

Most existing face image Super-Resolution (SR) methods assume that the L...

Towards Unpaired Depth Enhancement and Super-Resolution in the Wild

Depth maps captured with commodity sensors are often of low quality and ...

Dual-reference Training Data Acquisition and CNN Construction for Image Super-Resolution

For deep learning methods of image super-resolution, the most critical i...

Code Repositories


To learn image super-resolution, use a GAN to learn how to do image degradation first, ECCV 2018

view repo


Can we perform face hallucination using limited set of unaligned pairs?

view repo