Mutual Guidance and Residual Integration for Image Enhancement

TL;DR

This paper introduces a mutual guidance network with residual integration for image enhancement, effectively balancing global and local information exchange to achieve state-of-the-art results efficiently.

Contribution

It proposes a novel bidirectional global-local information exchange framework with residual integration, addressing limitations of existing CNN and transformer-based models.

Findings

Achieves state-of-the-art performance on public benchmarks.

Demonstrates effective global-local information fusion.

Maintains computational efficiency with a compact architecture.

Abstract

Previous studies show the necessity of global and local adjustment for image enhancement. However, existing convolutional neural networks (CNNs) and transformer-based models face great challenges in balancing the computational efficiency and effectiveness of global-local information usage. Especially, existing methods typically adopt the global-to-local fusion mode, ignoring the importance of bidirectional interactions. To address those issues, we propose a novel mutual guidance network (MGN) to perform effective bidirectional global-local information exchange while keeping a compact architecture. In our design, we adopt a two-branch framework where one branch focuses more on modeling global relations while the other is committed to processing local information. Then, we develop an efficient attention-based mutual guidance approach throughout our framework for bidirectional global-local interactions. As a result, both the global and local branches can enjoy the merits of mutual information aggregation. Besides, to further refine the results produced by our MGN, we propose a novel residual integration scheme following the divide-and-conquer philosophy. The extensive experiments demonstrate the effectiveness of our proposed method, which achieves state-of-the-art performance on several public image enhancement benchmarks.