Super-resolution based generative adversarial network using visual perceptual loss function release_gy2uztvkozgmlhfpzaejb4zbwy

by Xuan Zhu and Yue Cheng and Rongzhi Wang

Released as a article .

2019  

Abstract

In recent years, perceptual-quality driven super-resolution methods show satisfactory results. However, super-resolved images have uncertain texture details and unpleasant artifact. We build a novel perceptual loss function composed of morphological components adversarial loss and color adversarial loss and salient content loss to ameliorate these problems. The adversarial loss is applied to constrain color and morphological components distribution of super-resolved images and the salient content loss highlights the perceptual similarity of feature-rich regions. Experiments show that proposed method achieves significant improvements in terms of perceptual index and visual quality compared with the state-of-the-art methods.
In text/plain format

Archived Files and Locations

application/pdf  1.2 MB
file_yu3pwzki4zfrxkfnfn772fn7my
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-04-24
Version   v1
Language   en ?
arXiv  1904.10654v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: ce47492b-ba29-4d46-9332-d5fec6eeff03
API URL: JSON