期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 24, 期 -, 页码 1366-1377出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2021.3063916
关键词
Image restoration; Task analysis; Collaboration; Image denoising; Finite element analysis; Computer architecture; Training; Deep neural network; feature fusion; image denoising; non-local attention; image restoration
资金
- Key-Area Research, and Development Program of Guangdong Province [2019B121204008]
- National Natural Science Foundation of China [61902009]
- Shenzhen Research Project [201806080921419290]
This paper proposes a novel collaborative attention network (COLA-Net) for image restoration, which combines local and non-local attention mechanisms to restore image content in areas with complex textures and highly repetitive details. By developing an effective and robust patch-wise non-local attention model, long-range feature correspondences are captured.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据