Identity Enhanced Residual Image Denoising

被引:10
作者
Anwar, Saeed [1 ,2 ]
Cong Phuoc Huynh [2 ]
Porikli, Fatih [2 ]
机构
[1] Data61 CSIRO, Sydney, NSW, Australia
[2] Australian Natl Univ, Canberra, ACT, Australia
来源
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020) | 2020年
关键词
ALGORITHM;
D O I
10.1109/CVPRW50498.2020.00268
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose to learn a fully-convolutional network model that consists of a Chain of Identity Mapping Modules and residual on the residual architecture for image denoising. Our network structure possesses three distinctive features that are important for the noise removal task. Firstly, each unit employs identity mappings as the skip connections and receives pre-activated input to preserve the gradient magnitude propagated in both the forward and backward directions. Secondly, by utilizing dilated kernels for the convolution layers in the residual branch, each neuron in the last convolution layer of each module can observe the full receptive field of the first layer. Lastly, we employ the residual on the residual architecture to ease the propagation of the high-level information. Contrary to current state-of-the-art real denoising networks, we also present a straightforward and single-stage network for real image denoising. The proposed network produces remarkably higher numerical accuracy and better visual image quality than the classical state-of-the-art and CNN algorithms when being evaluated on the three conventional benchmark and three real-world datasets.
引用
收藏
页码:2201 / 2210
页数:10
相关论文
共 57 条
[21]   Pointwise shape-adaptive DCT for high-quality denoising and deblocking of grayscale and color images [J].
Foi, Alessandro ;
Katkovnik, Vladimir ;
Egiazarian, Karen .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (05) :1395-1411
[22]  
GOOSSENS B, 2008, INT WORKSH LOC NONL, P143
[23]   Weighted Nuclear Norm Minimization with Application to Image Denoising [J].
Gu, Shuhang ;
Zhang, Lei ;
Zuo, Wangmeng ;
Feng, Xiangchu .
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, :2862-2869
[24]  
Guo Shi, 2018, ARXIV180704686
[25]   Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :1026-1034
[26]   Identity Mappings in Deep Residual Networks [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 :630-645
[27]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[28]   Face detection:: A survey [J].
Hjelmås, E ;
Low, BK .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2001, 83 (03) :236-274
[29]  
Kingma DP, 2014, ADV NEUR IN, V27
[30]   A Nonlocal Bayesian Image Denoising Algorithm [J].
Lebrun, M. ;
Buades, A. ;
Morel, J. M. .
SIAM JOURNAL ON IMAGING SCIENCES, 2013, 6 (03) :1665-1688