Efficient generative model for motion deblurring

This article proposes a generate model for motion deblurring based on generative adversarial network. The generate model adopts multi-level and multi-scale feature fusion structure. By concatenating different scales of images and feature maps and adding them by pixels, the image details of each leve...

Full description

Saved in:
Bibliographic Details
Published in:Journal of engineering (Stevenage, England) England), 2020-07, Vol.2020 (13), p.491-494
Main Authors: Xiang, Han, Sang, Haiwei, Sun, Lilei, Zhao, Yong
Format: Article
Language:English
Subjects:
enlargement part
feature extraction
generated model
generative adversarial network
generative model
image details
image fusion
image motion analysis
image restoration
learning (artificial intelligence)
motion deblurring
neural nets
pixel level
The 3rd Asian Conference on Artificial Intelligence Technology (ACAIT 2019)
training convergence
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article proposes a generate model for motion deblurring based on generative adversarial network. The generate model adopts multi-level and multi-scale feature fusion structure. By concatenating different scales of images and feature maps and adding them by pixels, the image details of each level are obtained. The enlargement part of feature maps uses three branches, which can generate more rich and realistic detail. In the training process, three loss functions at the pixel level and the abstract level are used to make the training convergence faster and effectively assist the parameter learning of the generated model. Experiments show that the proposed approach is more efficient than many state-of-the-art methods.
ISSN:2051-3305
2051-3305
DOI:10.1049/joe.2019.1163