Densely connected hierarchical network for image denoising
- Authors
- Park, Bumjun; Yu, Songhyun; Jeong, Je chang
- Issue Date
- Jun-2019
- Publisher
- IEEE Computer Society
- Citation
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, v.2019, no.June, pp.2104 - 2113
- Indexed
- SCOPUS
- Journal Title
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
- Volume
- 2019
- Number
- June
- Start Page
- 2104
- End Page
- 2113
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/3813
- DOI
- 10.1109/CVPRW.2019.00263
- ISSN
- 2160-7508
- Abstract
- Recently, deep convolutional neural networks have been applied in numerous image processing researches and have exhibited drastically improved performances. In this study, we introduce a densely connected hierarchical image denoising network (DHDN), which exceeds the performances ofstate-of-the-art image denoising solutions. Our proposed network improves the image denoising performance by applying the hierarchical architecture of the modified U-Net; this enables our network to use a larger number ofparameters than other methods. In addition, we induce feature reuse and solve the vanishing-gradient problem by applying dense connectivity and residual learning to our convolution blocks and network. Finally, we successfully apply the model ensemble and self-ensemble methods; this enables us to improve the performance of the proposed network. The performance of the proposed network is validated by winning the second place in the NTRIE 2019 real image denoising challenge sRGB track and the third place in the raw-RGB track. Additional experimental results on additive white Gaussian noise removal also establish that the proposed network outperforms conventional methods; this is notwithstanding the fact that the proposed network handles a wide range of noise levels with a single set of trained parameters.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/3813)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.