Image Inpainting Using Wasserstein Generative Adversarial Imputation Network

TL;DR

This paper introduces a Wasserstein GAN-based model for image inpainting that effectively reconstructs missing regions across various scenarios, demonstrating high-quality results on benchmark datasets.

Contribution

The paper presents a novel Wasserstein GAN architecture with convolutional and skip connections for versatile and high-quality image inpainting across different missingness scenarios.

Findings

Achieves high PSNR and SSIM scores on CelebA and Paris datasets.

Performs better than biharmonic and some state-of-the-art methods.

Handles multiple missingness scenarios with a single model.

Abstract

Image inpainting is one of the important tasks in computer vision which focuses on the reconstruction of missing regions in an image. The aim of this paper is to introduce an image inpainting model based on Wasserstein Generative Adversarial Imputation Network. The generator network of the model uses building blocks of convolutional layers with different dilation rates, together with skip connections that help the model reproduce fine details of the output. This combination yields a universal imputation model that is able to handle various scenarios of missingness with sufficient quality. To show this experimentally, the model is simultaneously trained to deal with three scenarios given by missing pixels at random, missing various smaller square regions, and one missing square placed in the center of the image. It turns out that our model achieves high-quality inpainting results on all scenarios. Performance is evaluated using peak signal-to-noise ratio and structural similarity index on two real-world benchmark datasets, CelebA faces and Paris StreetView. The results of our model are compared to biharmonic imputation and to some of the other state-of-the-art image inpainting methods.