Share Email Print
cover

Proceedings Paper

Image inpainting using Wasserstein Generative Adversarial Network
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Recent advances in convolution neural networks have shown promising results for the challenging task of filling large missing regions in an image with semantically plausible and context aware details. These learning-based methods are significantly more effective in capturing high-level features than prior techniques, but often create distorted structures or blurry textures inconsistent with existing areas. This is mainly due to ineffectiveness of convolutional neural networks in explicitly borrowing or copying information from distant locations. Motivated by these observations, we use a convolution neural networks architecture with Atrous Spatial Pyramid Pooling module, which can obtain multi-scale objection information, to be our inpainting network. We also use global and local Wasserstein discriminators that are jointly trained to distinguish real images from completed ones. We evaluate our approach on four datasets including faces (CelebA) and natural images (Paris Streetview, COCO, ImageNet) and achieved state-of-the-art inpainting accuracy.

Paper Details

Date Published: 7 September 2018
PDF: 12 pages
Proc. SPIE 10751, Optics and Photonics for Information Processing XII, 107510T (7 September 2018); doi: 10.1117/12.2320212
Show Author Affiliations
Peng Hua, Beijing Institute of Technology (China)
Xiaohua Liu, Beijing Institute of Technology (China)
Ming Liu, Beijing Institute of Technology (China)
Liquan Dong, Beijing Institute of Technology (China)
Mei Hui, Beijing Institute of Technology (China)
Yuejin Zhao, Beijing Institute of Technology (China)


Published in SPIE Proceedings Vol. 10751:
Optics and Photonics for Information Processing XII
Abdul A. S. Awwal; Khan M. Iftekharuddin; Mireya García Vázquez, Editor(s)

© SPIE. Terms of Use
Back to Top