CVMar 10, 2021

COLA-Net: Collaborative Attention Network for Image Restoration

arXiv:2103.05961v190 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses image restoration for applications like photography and medical imaging, offering an incremental improvement by integrating existing attention types.

The paper tackled image restoration by proposing COLA-Net, which combines local and non-local attention mechanisms to handle complex textures and repetitive details, achieving state-of-the-art performance in tasks like denoising and artifact reduction with improved computational efficiency.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes