Semantic Image Inpainting through Improved Wasserstein Generative Adversarial Networks

Patricia Vitoria, Joan Sintes, Coloma Ballester

2019

Abstract

Image inpainting is the task of filling-in missing regions of a damaged or incomplete image. In this work we tackle this problem not only by using the available visual data but also by incorporating image semantics through the use of generative models. Our contribution is twofold: First, we learn a data latent space by training an improved version of the Wasserstein generative adversarial network, for which we incorporate a new generator and discriminator architecture. Second, the learned semantic information is combined with a new optimization loss for inpainting whose minimization infers the missing content conditioned by the available data. It takes into account powerful contextual and perceptual content inherent in the image itself. The benefits include the ability to recover large regions by accumulating semantic information even it is not fully present in the damaged image. Experiments show that the presented method obtains qualitative and quantitative top-tier results in different experimental situations and also achieves accurate photo-realism comparable to state-of-the-art works.

Paper Citation

in Harvard Style

Vitoria P., Sintes J. and Ballester C. (2019). Semantic Image Inpainting through Improved Wasserstein Generative Adversarial Networks. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 249-260. DOI: 10.5220/0007367902490260

in Bibtex Style

@conference{visapp19,
author={Patricia Vitoria and Joan Sintes and Coloma Ballester},
title={Semantic Image Inpainting through Improved Wasserstein Generative Adversarial Networks},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP},
year={2019},
pages={249-260},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007367902490260},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP
TI - Semantic Image Inpainting through Improved Wasserstein Generative Adversarial Networks
SN - 978-989-758-354-4
AU - Vitoria P.
AU - Sintes J.
AU - Ballester C.
PY - 2019
SP - 249
EP - 260
DO - 10.5220/0007367902490260
PB - SciTePress