106 0

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


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE