Texture Memory-Augmented Deep Patch-Based Image Inpainting

TL;DR

This paper introduces a novel deep image inpainting framework that combines patch-based texture memory with deep learning, enabling high-quality, faithful, and sharp inpainting results for large missing regions.

Contribution

It presents a new texture memory-augmented deep inpainting method with end-to-end training and a patch distribution loss for improved inpainting quality.

Findings

Outperforms existing methods on Places, CelebA-HQ, and Paris Street-View datasets.

Achieves superior qualitative and quantitative inpainting results.

Effectively combines patch-based and deep learning approaches for large missing regions.

Abstract

Patch-based methods and deep networks have been employed to tackle image inpainting problem, with their own strengths and weaknesses. Patch-based methods are capable of restoring a missing region with high-quality texture through searching nearest neighbor patches from the unmasked regions. However, these methods bring problematic contents when recovering large missing regions. Deep networks, on the other hand, show promising results in completing large regions. Nonetheless, the results often lack faithful and sharp details that resemble the surrounding area. By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions. The framework has a novel design that allows texture memory retrieval to be trained end-to-end with the deep inpainting network. In addition, we introduce a patch distribution loss to encourage high-quality patch synthesis. The proposed method shows superior performance both qualitatively and quantitatively on three challenging image benchmarks, i.e., Places, CelebA-HQ, and Paris Street-View datasets.