Adaptive Diagonal Total-Variation Generative Adversarial Network for Super-Resolution Imaging

To address problems that the loss function does not correlate well with perceptual vision in super-resolution methods based on the convolutional neural network(CNN), a novel model called the ADTV-SRGAN is designed based on the adaptive diagonal total-variation generative adversarial network. Combine...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020, Vol.8, p.57517-57526
Main Authors: San-You, Zhang, De-Qiang, Cheng, Dai-Hong, Jiang, Qi-Qi, Kou, Lu, Ma
Format: Article
Language:English
Subjects:
Adaptation models
Artificial neural networks
Feature extraction
Gallium nitride
Generative adversarial network
Generative adversarial networks
Image edge detection
Image quality
Image reconstruction
Image resolution
loss function
Optimization
Subjective assessment
super-resolution imaging
total variation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To address problems that the loss function does not correlate well with perceptual vision in super-resolution methods based on the convolutional neural network(CNN), a novel model called the ADTV-SRGAN is designed based on the adaptive diagonal total-variation generative adversarial network. Combined with global perception and the local structure adaptive method, spatial loss based on the diagonal variation model is proposed to make the loss function can be adjusted according to the spatial features. Pixel loss and characteristic loss are in combination with the spatial loss for the fusing optimization of the total loss function such that high-frequency details of the images are maintained to improve their quality. The results of experiment show that the proposed method can obtain competitive results in objective evaluations. In subjective assessment, images reconstructed by it are clear, delicate, and natural, and it preserved edge- and texture-related details.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.2981726