Image Enhancement by Recurrently-trained Super-resolution Network

07/26/2019
by   Saem Park, et al.
0

We introduce a new learning strategy for image enhancement by recurrently training the same simple superresolution (SR) network multiple times. After initially training an SR network by using pairs of a corrupted low resolution (LR) image and an original image, the proposed method makes use of the trained SR network to generate new high resolution (HR) images with a doubled resolution from the original uncorrupted images. Then, the new HR images are downscaled to the original resolution, which work as target images for the SR network in the next stage. The newly generated HR images by the repeatedly trained SR network show better image quality and this strategy of training LR to mimic new HR can lead to a more efficient SR network. Up to a certain point, by repeating this process multiple times, better and better images are obtained. This recurrent leaning strategy for SR can be a good solution for downsizing convolution networks and making a more efficient SR network. To measure the enhanced image quality, for the first time in this area of super-resolution and image enhancement, we use VIQET MOS score which reflects human visual quality more accurately than the conventional MSE measure.

READ FULL TEXT

page 1

page 6

research
10/15/2018

Lesion Focused Super-Resolution

Super-resolution (SR) for image enhancement has great importance in medi...
research
05/07/2019

Trinity of Pixel Enhancement: a Joint Solution for Demosaicking, Denoising and Super-Resolution

Demosaicing, denoising and super-resolution (SR) are of practical import...
research
08/03/2020

Fusion of Deep and Non-Deep Methods for Fast Super-Resolution of Satellite Images

In the emerging commercial space industry there is a drastic increase in...
research
01/21/2019

Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy

In recent years, endomicroscopy has become increasingly used for diagnos...
research
03/10/2021

Super-Resolving Beyond Satellite Hardware Using Realistically Degraded Images

Modern deep Super-Resolution (SR) networks have established themselves a...
research
10/09/2022

Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images

Rendering high-resolution (HR) graphics brings substantial computational...
research
02/07/2018

Super-resolution of spatiotemporal event-based image

Super-resolution (SR) is a useful technology to generate a high-resoluti...

Please sign up or login with your details

Forgot password? Click here to reset