Image Fine-grained Inpainting

TL;DR

This paper introduces a one-stage GAN-based image inpainting model that uses dense dilated convolutions, novel loss functions, and a dual-branch discriminator to produce more realistic and structurally coherent inpainted images, outperforming existing methods.

Contribution

The paper proposes a novel one-stage inpainting model with dense dilated convolutions, a self-guided regression loss, and a dual-branch discriminator with feature matching, improving inpainting quality and structure recovery.

Findings

Outperforms state-of-the-art inpainting methods on public datasets.

Effectively recovers large missing regions with improved structural coherence.

Enhances semantic detail and local-global content consistency.

Abstract

Image inpainting techniques have shown promising improvement with the assistance of generative adversarial networks (GANs) recently. However, most of them often suffered from completed results with unreasonable structure or blurriness. To mitigate this problem, in this paper, we present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. Benefited from the property of this network, we can more easily recover large regions in an incomplete image. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss for concentrating on uncertain areas and enhancing the semantic details. Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones. We also employ a discriminator with local and global branches to ensure local-global contents consistency. To further improve the quality of generated images, discriminator feature matching on the local branch is introduced, which dynamically minimizes the similarity of intermediate features between synthetic and ground-truth patches. Extensive experiments on several public datasets demonstrate that our approach outperforms current state-of-the-art methods. Code is available at https://github.com/Zheng222/DMFN.