Deep Iterative Down-Up CNN for Image Denoising
- Title
- Deep Iterative Down-Up CNN for Image Denoising
- Author
- 정제창
- Keywords
- Convolution; Image denoising; Noise level; Image resolution; Graphics processing units; Feature extraction; Memory management
- Issue Date
- 2019-06
- Publisher
- IEEE
- Citation
- CVPR Workshops 2019, Page. 1-9
- Abstract
- Networks using down-scaling and up-scaling of feature maps have been studied extensively in low-level vision research owing to efficient GPU memory usage and their capacity to yield large receptive fields. In this paper, we propose a deep iterative down-up convolutional neural network (DIDN) for image denoising, which repeatedly decreases and increases the resolution of the feature maps. The basic structure of the network is inspired by U-Net which was originally developed for semantic segmentation. We modify the down-scaling and up-scaling layers for image denoising task. Conventional denoising networks are trained to work with a single-level noise, or alternatively use noise information as inputs to address multi-level noise
with a single model. Conversely, because the efficient memory usage of our network enables it to handle multiple parameters, it is capable of processing a wide range of noise levels with a single model without requiring noiseinformation inputs as a work-around. Consequently, our DIDN exhibits state-of-the-art performance using the benchmark dataset and also demonstrates its superiority in the NTIRE 2019 real image denoising challenge.
- URI
- https://ieeexplore.ieee.org/document/9025411https://repository.hanyang.ac.kr/handle/20.500.11754/151475
- ISBN
- 978-1-7281-2506-0
- ISSN
- 2160-7516
- DOI
- 10.1109/CVPRW.2019.00262
- Appears in Collections:
- COLLEGE OF ENGINEERING[S](공과대학) > ELECTRONIC ENGINEERING(융합전자공학부) > Articles
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML