Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks.
Entropy (Basel)
; 24(8)2022 Jul 26.
Article
en En
| MEDLINE
| ID: mdl-35893009
ABSTRACT
Convolutional neural networks have greatly improved the performance of image super-resolution. However, perceptual networks have problems such as blurred line structures and a lack of high-frequency information when reconstructing image textures. To mitigate these issues, a generative adversarial network based on multiscale asynchronous learning is proposed in this paper, whereby a pyramid structure is employed in the network model to integrate high-frequency information at different scales. Our scheme employs a U-net as a discriminator to focus on the consistency of adjacent pixels in the input image and uses the LPIPS loss for perceptual extreme super-resolution with stronger supervision. Experiments on benchmark datasets and independent datasets Set5, Set14, BSD100, and SunHays80 show that our approach is effective in restoring detailed texture information from low-resolution images.
Texto completo:
1
Banco de datos:
MEDLINE
Idioma:
En
Revista:
Entropy (Basel)
Año:
2022
Tipo del documento:
Article
País de afiliación:
China