Multi-scale patch-GAN with edge detection for image inpainting

Image inpainting with large missing blocks is quite challenging to obtain visual consistency and realistic effect. In this paper, the multi-scale patch generative adversarial networks with edge detection image inpainting (MPGE) was proposed. Firstly, an edge detector was introduced into the generato...

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2023-02, Vol.53 (4), p.3917-3932
Main Authors: Chen, Gang, Zhang, Guipeng, Yang, Zhenguo, Liu, Wenyin
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Computer Science
Consistency
Deep learning
Dictionaries
Diffusion
Edge detection
Generative adversarial networks
Machines
Manufacturing
Mechanical Engineering
Processes
Subspaces
Visual effects
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:Image inpainting with large missing blocks is quite challenging to obtain visual consistency and realistic effect. In this paper, the multi-scale patch generative adversarial networks with edge detection image inpainting (MPGE) was proposed. Firstly, an edge detector was introduced into the generator of multi-scale generative adversarial networks (GAN) to guide the inpainting of the edge contour in the image inpainting, which improved the inpainting effect of image posture and expression. Secondly, we designed a patch-GAN as the local discriminant to capture high frequency, and a function L 2 -loss was utilized to keep the high resolution and style of the original image. Thirdly, a multi-head attention mechanism was introduced into the generator and local discriminator to build a multilevel and multi-dimensional dependent network model for image subspaces, which improved the global consistency of the inpainted image. Finally, by finding the minimum data set with similar network expression ability, we quickly obtained the optimal value of multi-head. Thereby, a lot of training time was saved. The experiments conducted on Celeba dataset proved that our proposed algorithm quantitatively and qualitatively outperformed the baselines.
ISSN:0924-669X
1573-7497
DOI:10.1007/s10489-022-03577-2