Image Inpainting With Learnable Edge-Attention Maps

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

Bibliographic Details
Main Authors: Liujie Sun, Qinghan Zhang, Wenju Wang, Mingxi Zhang
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Image inpainting
attention module
edge map
dual-discriminator
Online Access:https://ieeexplore.ieee.org/document/9309236/

Similar Items

Similar Items