Image Inpainting With Learnable Edge-Attention Maps

This paper proposes an end-to-end Learnable Edge-Attention Map (LEAM) method to assist image inpainting. To achieve a better-recovered effect, we design an edge attention module, which extracts the feature information of the edge map and re-normalizes the image feature information when automatically...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2021-01, Vol.9, p.3816-3827
Main Authors: Sun, Liujie, Zhang, Qinghan, Wang, Wenju, Zhang, Mingxi
Format: Article
Language:English
Subjects:
attention module
Convolution
Data mining
Decoding
dual-discriminator
edge map
Feature extraction
Generators
Image edge detection
Image inpainting
Image quality
Semantics
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:This paper proposes an end-to-end Learnable Edge-Attention Map (LEAM) method to assist image inpainting. To achieve a better-recovered effect, we design an edge attention module, which extracts the feature information of the edge map and re-normalizes the image feature information when automatically updating the edge map. And the information of known regions is adopted to assist the decoder generates semantically consistent results. A dual-discriminator structure consisting of the local discriminator and global discriminator is proposed to generate realistic texture details and improve the consistency of the overall structure. Experiments show that our method can obtain higher image inpainting quality than the existing state-of-the-art approaches, which improves PSNR by 3.58%, SSIM by 2.27%, and reduce MAE by 9.21% on average.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.3047740