Abstract | ||
---|---|---|
With the fast development of deep learning models, hierarchical convolutional neural networks have achieved great success in image denoising tasks. To further boost the performance of image denoising, a novel non-local hierarchical network (NHNet) is proposed. Unlike existing U-Net-based hierarchical methods, which mainly focus on downsampling operations, NHNet adopts an initial resolution path and a high resolution path. Specifically, the high-resolution features are obtained through upsampling, where the non-local mechanism is adopted to capture the self-similarity properties, which contribute to a better denoising performance. Cross connections and channel attention layers are added between the two paths to integrate features in different resolutions. Compared with other U-Net-based hierarchical networks, NHNet requires fewer parameters. Experiments show that NHNet achieves state-of-the-art performance in Gaussian denoising tasks and gets competitive results when dealing with real image denoising. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1049/ipr2.12499 | IET IMAGE PROCESSING |
DocType | Volume | Issue |
Journal | 16 | 9 |
ISSN | Citations | PageRank |
1751-9659 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiahong Zhang | 1 | 0 | 0.34 |
Lihong Cao | 2 | 0 | 1.69 |
Wang Tian | 3 | 17 | 15.16 |
Wenlong Fu | 4 | 0 | 0.34 |
Weiheng Shen | 5 | 0 | 0.34 |