DEGAN: Discrimination Enhanced GAN for Perceptual-Oriented Super-Resolution
Xiaoyu Jin, Wenqi Huang, Lingyu Liang, Yang Wu, Qunsheng Zeng, Ruiye Zhou, Zhuojun Cai, Jianing Shang
Abstract
Recent years, generative adversarial networks (GANs) have gained significant prominence in single image super-resolution (SISR) tasks. This can mainly be attributed to their exceptional ability to generate intricate details. However, the instability and lack of realism in the details generated by GANs have been challenges. Existing methods mainly concentrate on improving the generator and designing complex loss functions, often overlooking the important role of discrimination. To this end, we propose our discrimination enhanced GAN (DEGAN) by improving the discriminator and simplify the discrimination task. We introduce an efficient wide activation UNet to enhance the discriminator, enabling a more comprehensive and nuanced analysis of the input image. Additionally, we introduce a texture aware mask that provides more precise guidance and alleviates the difficulty of discrimination. Our DEGAN is simple yet effective. Quantitative and visual comparisons with state-of-the-art methods on benchmark datasets demonstrate the superiority of our method.
BibTeX
@inproceedings{icassp2024_degandiscriminat,
title = {DEGAN: Discrimination Enhanced GAN for Perceptual-Oriented Super-Resolution},
author = {Xiaoyu Jin and Wenqi Huang and Lingyu Liang and Yang Wu and Qunsheng Zeng and Ruiye Zhou and Zhuojun Cai and Jianing Shang and Wenming Yang},
booktitle = {ICASSP 2024},
year = {2024}
}