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

TL;DR

This paper introduces S-WGAN, a novel high-resolution facial image inpainting method using symmetric skip connections and Wasserstein-Perceptual loss, resulting in sharper, more realistic images with superior SSIM scores.

Contribution

The paper proposes a new S-WGAN architecture with skip connections and a Wasserstein-Perceptual loss for improved high-resolution facial image inpainting.

Findings

S-WGAN produces sharper, more realistic images visually.

Achieves the highest SSIM of 0.94 on CelebA-HQ.

Outperforms state-of-the-art methods in image quality.

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.