Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks

Thang Vu, Tung M. Luu, Chang D. Yoo

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 .
BibTeX
@inproceedings{vu2018perception,
  author = {Thang Vu and Tung M. Luu and Chang D. Yoo},
  title = {{Perception-Enhanced Image Super-Resolution via Relativistic Generative Adversarial Networks}},
  booktitle = {Workshops @ ECCV},
  year = {2018},
  doi = {10.1007/978-3-030-11021-5\_7},
}

Loading related content...

Figure