Improving Image Super-Resolution Based on Multiscale Generative Adversarial Networks

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 ne...

Descripción completa

Detalles Bibliográficos
Autores principales: Yuan, Cao, Deng, Kaidi, Li, Chen, Zhang, Xueting, Li, Yaqin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9394415/
https://www.ncbi.nlm.nih.gov/pubmed/35893009
http://dx.doi.org/10.3390/e24081030

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9394415/
https://www.ncbi.nlm.nih.gov/pubmed/35893009
http://dx.doi.org/10.3390/e24081030

Ejemplares similares