An Edge Information and Mask Shrinking Based Image Inpainting Approach

TL;DR

This paper introduces a novel image inpainting method that combines edge information and mask shrinking strategies to effectively restore both high-frequency and low-frequency details, outperforming existing techniques.

Contribution

It proposes a dual-model approach with edge generation and mask shrinking, addressing the limitation of previous methods in handling both frequency information simultaneously.

Findings

Outperforms state-of-the-art methods on Places2 dataset

Effectively restores both high-frequency and low-frequency details

Uses a novel mask shrinking strategy for improved inpainting

Abstract

In the image inpainting task, the ability to repair both high-frequency and low-frequency information in the missing regions has a substantial influence on the quality of the restored image. However, existing inpainting methods usually fail to consider both high-frequency and low-frequency information simultaneously. To solve this problem, this paper proposes edge information and mask shrinking based image inpainting approach, which consists of two models. The first model is an edge generation model used to generate complete edge information from the damaged image, and the second model is an image completion model used to fix the missing regions with the generated edge information and the valid contents of the damaged image. The mask shrinking strategy is employed in the image completion model to track the areas to be repaired. The proposed approach is evaluated qualitatively and quantitatively on the dataset Places2. The result shows our approach outperforms state-of-the-art methods.