Symmetric Skip Connection Wasserstein GAN for High-resolution Facial Image Inpainting

Jireh Jam, Connah Kendrick, Vincent Drouard, Kevin Walker, Gee-Sern Hsu, Moi Hoon Yap

2021

Abstract

The state-of-the-art facial image inpainting methods achieved promising results but face realism preservation remains a challenge. This is due to limitations such as; failures in preserving edges and blurry artefacts. To overcome these limitations, we propose a Symmetric Skip Connection Wasserstein Generative Adversarial Network (S-WGAN) for high-resolution facial image inpainting. The architecture is an encoder-decoder with convolutional blocks, linked by skip connections. The encoder is a feature extractor that captures data abstractions of an input image to learn an end-to-end mapping from an input (binary masked image) to the ground-truth. The decoder uses learned abstractions to reconstruct the image. With skip connections, S-WGAN transfers image details to the decoder. Additionally, we propose a Wasserstein-Perceptual loss function to preserve colour and maintain realism on a reconstructed image. We evaluate our method and the state-of-the-art methods on CelebA-HQ dataset. Our results show S-WGAN produces sharper and more realistic images when visually compared with other methods. The quantitative measures show our proposed S-WGAN achieves the best Structure Similarity Index Measure (SSIM) of 0.94.

Download


Paper Citation


in Harvard Style

Jam J., Kendrick C., Drouard V., Walker K., Hsu G. and Yap M. (2021). Symmetric Skip Connection Wasserstein GAN for High-resolution Facial Image Inpainting. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 35-44. DOI: 10.5220/0010188700350044


in Bibtex Style

@conference{visapp21,
author={Jireh Jam and Connah Kendrick and Vincent Drouard and Kevin Walker and Gee-Sern Hsu and Moi Hoon Yap},
title={Symmetric Skip Connection Wasserstein GAN for High-resolution Facial Image Inpainting},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={35-44},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010188700350044},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - Symmetric Skip Connection Wasserstein GAN for High-resolution Facial Image Inpainting
SN - 978-989-758-488-6
AU - Jam J.
AU - Kendrick C.
AU - Drouard V.
AU - Walker K.
AU - Hsu G.
AU - Yap M.
PY - 2021
SP - 35
EP - 44
DO - 10.5220/0010188700350044
PB - SciTePress