Recently, generative adversarial network-based image super resolution has been investigated, and it has been shown to lead to overwhelming improvements in subjective quality. However, it also leads to checkerboard artifacts and the unpleasing high-frequency (HF) components. In this paper, we propose a multi-discriminators-based image super resolution method that distinguishes those artifacts from various perspectives. First, the DCT perspective discriminator is proposed because the checkerboard artifacts are easily separated on the frequency domain. Second, the gradient perspective discriminator is proposed, because the unpleasing HF components can be discriminated on the gradient magnitude distribution. These proposed multi-perspective discriminators can easily identify artifacts, and they can help the generator reproduce artifact-less SR images. The experimental results show that the proposed SR-GAN with multi-perspective discriminators achieves objective and subjective quality improvements in terms of PSNR, SSIM, PI and MOS, as compared to the conventional SR-GAN by reducing the aforementioned artifacts.
Bibliographical noteFunding Information:
This work was supported in part by the National Research Foundation of Korea (NRF) through the Korean Government (MSIT) under Grant 2019R1A2C1005834, and in part by the Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center (ITRC) Support Program supervised by the Institute of Information and Communications Technology Planning and Evaluation (IITP) under Grant IITP-2019-2018-0-01421.
© 2013 IEEE.
- Image super-resolution
- SR GAN
- deep learning for super resolution
ASJC Scopus subject areas
- General Computer Science
- General Materials Science
- General Engineering