COLA-Net: Collaborative Attention Network for Image Restoration

TL;DR

COLA-Net introduces a novel approach that combines local and non-local attention mechanisms to improve image restoration, effectively handling complex textures and repetitive details with state-of-the-art results.

Contribution

It is the first to integrate local and non-local attention mechanisms for image restoration, enhancing performance on complex textures and repetitive details.

Findings

Achieves state-of-the-art PSNR and visual quality in denoising and artifact reduction.

Develops a robust patch-wise non-local attention model for long-range feature capture.

Maintains computational efficiency while improving restoration quality.

Abstract

Local and non-local attention-based methods have been well studied in various image restoration tasks while leading to promising performance. However, most of the existing methods solely focus on one type of attention mechanism (local or non-local). Furthermore, by exploiting the self-similarity of natural images, existing pixel-wise non-local attention operations tend to give rise to deviations in the process of characterizing long-range dependence due to image degeneration. To overcome these problems, in this paper we propose a novel collaborative attention network (COLA-Net) for image restoration, as the first attempt to combine local and non-local attention mechanisms to restore image content in the areas with complex textures and with highly repetitive details respectively. In addition, an effective and robust patch-wise non-local attention model is developed to capture long-range feature correspondences through 3D patches. Extensive experiments on synthetic image denoising, real image denoising and compression artifact reduction tasks demonstrate that our proposed COLA-Net is able to achieve state-of-the-art performance in both peak signal-to-noise ratio and visual perception, while maintaining an attractive computational complexity. The source code is available on https://github.com/MC-E/COLA-Net.