Bi-GANs-ST for Perceptual Image Super-resolution

11/01/2018
by   Xiaotong Luo, et al.
2

Image quality measurement is a critical problem for image super-resolution (SR) algorithms. Usually, they are evaluated by some well-known objective metrics, e.g., PSNR and SSIM, but these indices cannot provide suitable results in accordance with the perception of human being. Recently, a more reasonable perception measurement has been proposed in [1], which is also adopted by the PIRM-SR 2018 challenge. In this paper, motivated by [1], we aim to generate a high-quality SR result which balances between the two indices, i.e., the perception index and root-mean-square error (RMSE). To do so, we design a new deep SR framework, dubbed Bi-GANs-ST, by integrating two complementary generative adversarial networks (GAN) branches. One is memory residual SRGAN (MR-SRGAN), which emphasizes on improving the objective performance, such as reducing the RMSE. The other is weight perception SRGAN (WP-SRGAN), which obtains the result that favors better subjective perception via a two-stage adversarial training mechanism. Then, to produce final result with excellent perception scores and RMSE, we use soft-thresholding method to merge the results generated by the two GANs. Our method performs well on the perceptual image super-resolution task of the PIRM 2018 challenge. Experimental results on five benchmarks show that our proposal achieves highly competent performance compared with other state-of-the-art methods.

READ FULL TEXT

page 5

page 10

page 11

page 12

research
08/18/2019

RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution

Generative Adversarial Networks (GAN) have demonstrated the potential to...
research
05/07/2022

SPQE: Structure-and-Perception-Based Quality Evaluation for Image Super-Resolution

The image Super-Resolution (SR) technique has greatly improved the visua...
research
09/20/2018

2018 PIRM Challenge on Perceptual Image Super-resolution

This paper reports on the 2018 PIRM challenge on perceptual super-resolu...
research
02/02/2022

Unpaired Image Super-Resolution with Optimal Transport Maps

Real-world image super-resolution (SR) tasks often do not have paired da...
research
08/12/2023

BigWavGAN: A Wave-To-Wave Generative Adversarial Network for Music Super-Resolution

Generally, Deep Neural Networks (DNNs) are expected to have high perform...
research
11/30/2022

Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory

In recent years, multi-scale generative adversarial networks (GANs) have...
research
08/04/2022

Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution

Recently, single image super-resolution (SR) under large scaling factors...

Please sign up or login with your details

Forgot password? Click here to reset