research-article

Semantic image inpainting with boundary equilibrium GAN

Authors:

Yifan WangAuthors Info & Claims

AIPR '19: Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition

Pages 88 - 92

https://doi.org/10.1145/3357254.3357260

Published: 16 August 2019 Publication History

Get Access

Abstract

Recently, due to the vigorous development of deep learning, many methods in the field of image inpainting have been proposed which are different from the traditional image inpainting methods. This paper uses the high-quality image generation technology of BEGAN to complete the image inpainting task. Firstly, the image generation model is obtained by pretraining the generator and discriminator of BEGAN. Then this paper redesigns the loss function and finds the generated image suitable for the image inpainting task via gradient descent algorithm. By using the information contained in the undamaged part of the original image to be repaired, the BEGAN model can generate an image that is closest to the original image. Finally, the generated image is used to fill the lost area of the original image to be repaired, and the image inpainting task is completed. This paper confirms the validity of the method through the experiments on the CelebA and LFW datasets.

References

[1]

Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative Adversarial Networks. Advances in Neural Information Processing Systems, 2014, 3:2672--2680.

Digital Library

Google Scholar

[2]

Demir, U. and Unal, G. B. Patch-based image inpainting with generative adversarial nettworks. CoRR, abs/1803.07422, 2018.

Google Scholar

[3]

Ruohan Gao and Kristen Grauman. On-demand learning for deep imagerestoration. In Proc. IEEE Conf. Computer Vision and Pattern Recognition. 2017:1086--1095.

Google Scholar

[4]

Yan Z, Li X, Li M, et al. Shift-net: Image inpainting via deep feature rearrangement. Proceedings of the European Conference on Computer Vision (ECCV). 2018: 1--17.

Google Scholar

[5]

Yu J, Lin Z, Yang J, et al. Free-form image inpainting with gated convolution. arXiv preprint arXiv:1806.03589, 2018.

Google Scholar

[6]

M. Arjovsky and L. Bottou. Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862, 2017.

Google Scholar

[7]

David Berthelot, Tom Schumm, and Luke Metz. BEGAN: Boundary equilibrium generative adversarial networks. CoRR, abs/1703.10717, 2017.

Google Scholar

[8]

R. A. Yeh, C. Chen, T. Y. Lim, A. G. Schwing, M. Hasegawa-Johnson, and M. N. Do. Semantic image inpainting with deep generative models. In Conference on Computer Vision and Pattern Recognition (CVPR), pages 5485--5493, 2017.

Crossref

Google Scholar

[9]

Sutskever I, Martens J, Dahl G E, et al. On the importance of initialization and momentum in deep learning. ICML (3), 2013, 28(1139--1147): 5.

Google Scholar

[10]

Pérezp., Gangnetm., Blakea.: Poisson image editing.TOG (SIGGRAPH '03) 22(2003), 313--318.

Google Scholar

Cited By

View all

Stoean CBacanin NStoean RIonescu LAlecsa CHotoleanu MAtencia MJoya G(2022)On Using Perceptual Loss within the U-Net Architecture for the Semantic Inpainting of Textile Artefacts with Traditional Motifs2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)10.1109/SYNASC57785.2022.00051(276-283)Online publication date: Sep-2022
https://doi.org/10.1109/SYNASC57785.2022.00051

Index Terms

Semantic image inpainting with boundary equilibrium GAN
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems

Recommendations

Semantic Image Inpainting with Progressive Generative Networks
MM '18: Proceedings of the 26th ACM international conference on Multimedia

Recently, image inpainting task has revived with the help of deep learning techniques. Deep neural networks, especially the generative adversarial networks~(GANs) make it possible to recover the missing details in images. Due to the lack of sufficient ...
An Improved Method for Semantic Image Inpainting with GANs: Progressive Inpainting

Semantic image inpainting is getting more and more attention due to its increasing usage. Existing methods make inference based on either local data or external information. Generating Adversarial Networks, as a research focus in recent years, has been ...
Old Document Restoration using Super Resolution GAN and Semantic Image Inpainting
WAIE 2019: Proceedings of the International Workshop on Artificial Intelligence and Education

Restoration of damaged images is a fundamental problem that has been attempted before the advent of digital image processing technology. In this paper, one of the deep neural network technologies (GAN), we propose an image restoration network using ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

AIPR '19: Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition

August 2019

198 pages

ISBN:9781450372299

DOI:10.1145/3357254

Conference Chairs:
Li Ma
North China University of Technology, China
,
Xu Huang
University of Canberra, Australia

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 August 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Provincial Innovation and Entrepreneurship Planning Program for College Students
National Natural Science Foundation of China

Conference

AIPR 2019

AIPR 2019: 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition

August 16 - 18, 2019

Beijing, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
142
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Stoean CBacanin NStoean RIonescu LAlecsa CHotoleanu MAtencia MJoya G(2022)On Using Perceptual Loss within the U-Net Architecture for the Semantic Inpainting of Textile Artefacts with Traditional Motifs2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)10.1109/SYNASC57785.2022.00051(276-283)Online publication date: Sep-2022
https://doi.org/10.1109/SYNASC57785.2022.00051

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Semantic Image Inpainting with Progressive Generative Networks

An Improved Method for Semantic Image Inpainting with GANs: Progressive Inpainting

Old Document Restoration using Super Resolution GAN and Semantic Image Inpainting