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

07/30/2018
by   Adrian Bulat, et al.
6

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.

READ FULL TEXT

page 2

page 5

page 7

page 13

page 14

research
02/12/2021

A Generative Model for Hallucinating Diverse Versions of Super Resolution Images

Traditionally, the main focus of image super-resolution techniques is on...
research
03/28/2019

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...
research
12/07/2017

Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs

This paper addresses two challenging tasks: improving the quality of rea...
research
02/05/2021

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

Most existing face image Super-Resolution (SR) methods assume that the L...
research
05/25/2021

Towards Unpaired Depth Enhancement and Super-Resolution in the Wild

Depth maps captured with commodity sensors are often of low quality and ...
research
08/05/2021

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

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

Please sign up or login with your details

Forgot password? Click here to reset