A Novel Total Generalized Variation Model for Image Dehazing

被引:13
|
作者
Gu, Yanan [1 ]
Yang, Xiaoping [2 ]
Gao, Yiming [1 ]
机构
[1] Nanjing Univ Sci & Technol, Sch Sci, Nanjing 210094, Jiangsu, Peoples R China
[2] Nanjing Univ, Dept Math, Nanjing 210093, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
Dehaze; Atmospheric scatting model; TGV; Dark channel prior; REMOVAL;
D O I
10.1007/s10851-019-00909-9
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a new variational model for removing haze from a single input image. The proposed model combines two total generalized variation (TGV) regularizations, which are related to the image intensity and the transmission map, respectively, to build an optimization problem. Actually, TGV functionals are more appropriate for describing a natural color image and its transmission map with slanted plane. By minimizing the energy functional with double-TGV regularizations, we obtain the final haze-free image and the refined transmission map simultaneously instead of the general two-step framework. The existence and uniqueness of solutions to the proposed variational model are further obtained. Moreover, the variational model can be solved in a unified way by realizing a primal-dual method for associated saddle-point problems. A number of experimental results on natural hazy images are presented to demonstrate our superior performance, in comparison with some state-of-the-art methods in terms of the subjective and objective visual quality assessments. Compared with the total variation-based models, the proposed model can generate a haze-free image with less staircasing artifacts in the slanted plane and more details in the remote scene of an input image.
引用
收藏
页码:1329 / 1341
页数:13
相关论文
共 50 条
  • [21] Adapting total generalized variation for blind image restoration
    Wen-Ze Shao
    Feng Wang
    Li-Li Huang
    Multidimensional Systems and Signal Processing, 2019, 30 : 857 - 883
  • [22] A generalized relative total variation method for image smoothing
    Liu, Qiegen
    Xiong, Biao
    Yang, Dingcheng
    Zhang, Minghui
    MULTIMEDIA TOOLS AND APPLICATIONS, 2016, 75 (13) : 7909 - 7930
  • [23] SINGLE COLOR IMAGE DEHAZING BASED ON DIGITAL TOTAL VARIATION FILTER WITH COLOR TRANSFER
    Liu, Xuan
    Zeng, Fanxing
    Huang, Zhitong
    ji, Yuefeng
    2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013), 2013, : 909 - 913
  • [24] Visible and infrared image fusion using ?0-generalized total variation model
    Han PAN
    Zhongliang JING
    Lingfeng QIAO
    Minzhe LI
    ScienceChina(InformationSciences), 2018, 61 (04) : 265 - 276
  • [25] Visible and infrared image fusion using ℓ0-generalized total variation model
    Han Pan
    Zhongliang Jing
    Lingfeng Qiao
    Minzhe Li
    Science China Information Sciences, 2018, 61
  • [26] Image dehazing with dark channel prior and novel estimation model
    Huo, Bingquan
    Yin, Fengling
    International Journal of Multimedia and Ubiquitous Engineering, 2015, 10 (03): : 13 - 22
  • [27] Image denoising by a novel variable-order total fractional variation model
    Kazemi Golbaghi, Fariba
    Eslahchi, M. R.
    Rezghi, Mansoor
    MATHEMATICAL METHODS IN THE APPLIED SCIENCES, 2021, 44 (08) : 7250 - 7261
  • [28] A Novel Total Variation Model for Low-Dose CT Image Denoising
    Chen, Wenbin
    Shao, Yanling
    Wang, Yanling
    Zhang, Quan
    Liu, Yi
    Yao, Linhong
    Chen, Yan
    Yang, Guanru
    Gui, Zhiguo
    IEEE ACCESS, 2018, 6 : 78892 - 78903
  • [29] Single Image Dehazing With Depth-Aware Non-Local Total Variation Regularization
    Liu, Qi
    Gao, Xinbo
    He, Lihuo
    Lu, Wen
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (10) : 5178 - 5191
  • [30] Visible and infrared image fusion using l0-generalized total variation model
    Pan, Han
    Jing, Zhongliang
    Qiao, Lingfeng
    Li, Minzhe
    SCIENCE CHINA-INFORMATION SCIENCES, 2018, 61 (04)