RIDNet: Recursive Information Distillation Network for Color Image Denoising

被引:10
|
作者
Zhuo, Shengkai [1 ]
Jin, Zhi [1 ,2 ]
Zou, Wenbin [1 ]
Li, Xia [1 ]
机构
[1] Shenzhen Univ, Shenzhen, Peoples R China
[2] Sun Yat Sen Univ, Guangzhou, Peoples R China
来源
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW) | 2019年
基金
中国博士后科学基金;
关键词
FRAMEWORK;
D O I
10.1109/ICCVW.2019.00483
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Color image denoising is more challenging in effectiveness when comparing with the grayscale one. Most existing methods play a certain role in efficiency or flexibility, but lack robustness to handle various noise levels, especially the severe noise. This keeps them away from being practically applied to color image denoising. To address this issue, we propose a robust CNN based denoiser, namely Recursive Information Distillation Network (RIDNet), to handle the denoising task at high noise levels. The proposed RIDNet simultaneously keeps the efficiency and flexibility by introducing the information distillation module and merging a tunable noise level map as the input, respectively. Experiment results on Additive White Gaussian Noise (AWGN) images demonstrate that our method outperforms most of the state-of-the-art color image denoisers.
引用
收藏
页码:3896 / 3903
页数:8
相关论文
共 50 条
  • [1] Recursive radiography image denoising
    Ostojic, Vladimir S.
    Starcevic, Dorde S.
    Petrovic, Vladimir S.
    2017 25TH TELECOMMUNICATION FORUM (TELFOR), 2017, : 322 - 325
  • [2] Image denoising with sparsity distillation
    Multimedia Laboratory, Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Kanagawa
    212-8582, Japan
    IPSJ Trans. Comput. Vis. Appl., (50-54):
  • [3] Radar image denoising by recursive thresholding
    Chen, MY
    Chao, JJ
    INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, PROCEEDINGS - VOL I, 1996, : 395 - 398
  • [4] A Recursive Mean Filter for Image Denoising
    Erkan, Ugur
    Enginoglu, Serdar
    Thanh, Dang N. H.
    2019 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND DATA PROCESSING (IDAP 2019), 2019,
  • [5] Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation
    Li, Juncheng
    Yang, Hanhui
    Yi, Qiaosi
    Fang, Faming
    Gao, Guangwei
    Zeng, Tieyong
    Zhang, Guixu
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 557 - 566
  • [6] Polarized Color Image Denoising
    Li, Zhuoxiao
    Jiang, Haiyang
    Cao, Mingdeng
    Zheng, Yinqiang
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 9873 - 9882
  • [7] Color Image Denoising Using Reduced Biquaternion U-Network
    Nie, Bofan
    Gai, Shan
    Xiong, Gonghe
    IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 1119 - 1123
  • [8] FAST AND ROBUST RECURSIVE FILTER FOR IMAGE DENOISING
    Chi, Yiheng
    Chan, Stanley H.
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 1708 - 1712
  • [9] Adaptive multi-information distillation network for image dehazing
    Zhe Yu
    Jinye Peng
    Multimedia Tools and Applications, 2024, 83 : 18407 - 18426
  • [10] Toward Efficient Image Denoising: A Lightweight Network with Retargeting Supervision Driven Knowledge Distillation
    Zou, Beiji
    Zhang, Yue
    Wang, Min
    Liu, Shu
    ADVANCES IN COMPUTER GRAPHICS, CGI 2022, 2022, 13443 : 15 - 27