Multi-channel image inpainting algorithm based on edge prediction

Jianwen Liu; Ying Yang; Juan Zhang; Mingquan Zhou; Jiarui Xue

doi:10.1117/12.2623237

16 February 2022 Multi-channel image inpainting algorithm based on edge prediction

Jianwen Liu, Ying Yang, Juan Zhang, Mingquan Zhou, Jiarui Xue

Proceedings Volume 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021); 1208312 (2022) https://doi.org/10.1117/12.2623237
Event: Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 2021, Kunming, China

Abstract

This paper considers how to restore an image with large stained areas. An end to end model is proposed, which contains two networks, an edge generation adversarial network and a content generative adversarial network. First, the edge generation adversarial network is deployed to infer the missing boundaries of the image. Then the second network with a designed edge information channel is employed to restore the missing or stained areas of the image with the guidance of the inferred boundaries. Experiments were performed on ImageNet. The results show that the proposed model can better understand the semantic information of the stained area by introducing additional object contour channels and greatly improve the inpainting capability of the model. Quantitative evaluation indexes show that the proposed model is 4.5% better than the DeepFill V2 model in structural similarity and 7.1% better than the DeepFill V2 model in Peak Signal-to-Noise Ratio.

Citation Download Citation

Jianwen Liu, Ying Yang, Juan Zhang, Mingquan Zhou, and Jiarui Xue "Multi-channel image inpainting algorithm based on edge prediction", Proc. SPIE 12083, Thirteenth International Conference on Graphics and Image Processing (ICGIP 2021), 1208312 (16 February 2022); https://doi.org/10.1117/12.2623237

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

RGB color model

Image restoration

Convolution

Data modeling

Feature selection

Network architectures

Process modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years