Patch-Based Image Inpainting with Generative Adversarial Networks

TL;DR

This paper introduces PGGAN, a novel GAN-based image inpainting method that combines global and patch-level discriminators to effectively restore large missing regions with fewer artifacts.

Contribution

The paper proposes a new GAN architecture that integrates global and patch discriminators sharing layers, improving inpainting quality over existing methods.

Findings

Achieves superior visual quality in inpainting results.

Outperforms recent state-of-the-art methods quantitatively.

Reduces artifacts and noise in reconstructed regions.

Abstract

Area of image inpainting over relatively large missing regions recently advanced substantially through adaptation of dedicated deep neural networks. However, current network solutions still introduce undesired artifacts and noise to the repaired regions. We present an image inpainting method that is based on the celebrated generative adversarial network (GAN) framework. The proposed PGGAN method includes a discriminator network that combines a global GAN (G-GAN) architecture with a patchGAN approach. PGGAN first shares network layers between G-GAN and patchGAN, then splits paths to produce two adversarial losses that feed the generator network in order to capture both local continuity of image texture and pervasive global features in images. The proposed framework is evaluated extensively, and the results including comparison to recent state-of-the-art demonstrate that it achieves considerable improvements on both visual and quantitative evaluations.