Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks
Abstract
This paper considers a deep Generative Adversarial Networks (GAN) based method referred to as the Perception-Enhanced Super-Resolution (PESR) for Single Image Super Resolution (SISR) that enhances the perceptual quality of the reconstructed images by considering the following three issues: (1) ease GAN training by replacing an absolute with a relativistic discriminator, (2) include in the loss function a mechanism to emphasize difficult training samples which are generally rich in texture and (3) provide a flexible quality control scheme at test time to trade-off between perception and fidelity. Based on extensive experiments on six benchmark datasets, PESR outperforms recent state-of-the-art SISR methods in terms of perceptual quality. The code is available at https://github.com/thangvubk/PESR .
Cite
Text
Vu et al. "Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11021-5_7Markdown
[Vu et al. "Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/vu2018eccvw-perceptionenhanced/) doi:10.1007/978-3-030-11021-5_7BibTeX
@inproceedings{vu2018eccvw-perceptionenhanced,
title = {{Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks}},
author = {Vu, Thang and Luu, Tung Minh and Yoo, Chang D.},
booktitle = {European Conference on Computer Vision Workshops},
year = {2018},
pages = {98-113},
doi = {10.1007/978-3-030-11021-5_7},
url = {https://mlanthology.org/eccvw/2018/vu2018eccvw-perceptionenhanced/}
}