Dynamic Attentive Graph Learning for Image Restoration

TL;DR

This paper introduces a dynamic attentive graph learning model that adaptively explores non-local correlations at the patch level for improved image restoration, achieving state-of-the-art results across multiple tasks.

Contribution

It proposes a novel graph model with dynamic neighbors for patch-wise non-local correlation, enhancing message passing and restoration quality.

Findings

Achieves state-of-the-art results in image denoising, demosaicing, and artifact reduction.

Demonstrates superior accuracy and visual quality over existing methods.

Validates effectiveness across synthetic and real-world image restoration tasks.

Abstract

Non-local self-similarity in natural images has been verified to be an effective prior for image restoration. However, most existing deep non-local methods assign a fixed number of neighbors for each query item, neglecting the dynamics of non-local correlations. Moreover, the non-local correlations are usually based on pixels, prone to be biased due to image degradation. To rectify these weaknesses, in this paper, we propose a dynamic attentive graph learning model (DAGL) to explore the dynamic non-local property on patch level for image restoration. Specifically, we propose an improved graph model to perform patch-wise graph convolution with a dynamic and adaptive number of neighbors for each node. In this way, image content can adaptively balance over-smooth and over-sharp artifacts through the number of its connected neighbors, and the patch-wise non-local correlations can enhance the message passing process. Experimental results on various image restoration tasks: synthetic image denoising, real image denoising, image demosaicing, and compression artifact reduction show that our DAGL can produce state-of-the-art results with superior accuracy and visual quality. The source code is available at https://github.com/jianzhangcs/DAGL.