Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks

被引:9
|
作者
Ebenezer, Joshua Peter [1 ]
Das, Bijaylaxmi [1 ]
Mukhopadhyay, Sudipta [1 ]
机构
[1] Indian Inst Technol Kharagpur, Dept Elect & Elect Commun Engn, Kharagpur, W Bengal, India
关键词
VISIBILITY;
D O I
10.23919/eusipco.2019.8902992
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We present a method to restore a clear image from a haze-affected image using a Wasserstein generative adversarial network. As the problem is ill-conditioned, previous methods have required a prior on natural images or multiple images of the same scene. We train a generative adversarial network to learn the probability distribution of clear images conditioned on the haze-affected images using the Wasserstein loss function, using a gradient penalty to enforce the Lipschitz constraint. The method is data-adaptive, end-to-end, and requires no further processing or tuning of parameters. We also incorporate the use of a texture-based loss metric and the L1 loss to improve results, and show that our results are better than the current state-of-the-art.
引用
收藏
页数:5
相关论文
共 50 条
  • [21] StegGAN: hiding image within image using conditional generative adversarial networks
    Brijesh Singh
    Prasen Kumar Sharma
    Shashank Anil Huddedar
    Arijit Sur
    Pinaki Mitra
    Multimedia Tools and Applications, 2022, 81 : 40511 - 40533
  • [22] De-aliased seismic data interpolation using conditional Wasserstein generative adversarial networks
    Wei, Qing
    Li, Xiangyang
    Song, Mingpeng
    COMPUTERS & GEOSCIENCES, 2021, 154
  • [23] Single Image Cloud Removal Using U-Net and Generative Adversarial Networks
    Zheng, Jiahao
    Liu, Xiao-Yang
    Wang, Xiaodong
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (08): : 6371 - 6385
  • [24] Tile Art Image Generation using Conditional Generative Adversarial Networks
    Matsumura, Naoki
    Tokura, Hiroki
    Kuroda, Yuki
    Ito, Yasuaki
    Nakano, Koji
    2018 SIXTH INTERNATIONAL SYMPOSIUM ON COMPUTING AND NETWORKING WORKSHOPS (CANDARW 2018), 2018, : 209 - 215
  • [25] Multilevel Image Dehazing Algorithm Using Conditional Generative Adversarial Networks
    Gan, Kailei
    Zhao, Jieyu
    Chen, Hao
    IEEE ACCESS, 2020, 8 : 55221 - 55229
  • [26] Image shadow removal using cycle generative adversarial networks
    Tai, Shen-Chuan
    Chen, Peng-Yu
    Jiang, Xin-An
    JOURNAL OF ELECTRONIC IMAGING, 2019, 28 (01)
  • [27] Stereoscopic image reflection removal based on Wasserstein Generative Adversarial Network
    Wang, Xiuyuan
    Pan, Yikun
    Lun, Daniel P. K.
    2020 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), 2020, : 148 - 151
  • [28] Single Image Snow Removal via Composition Generative Adversarial networks
    Li, Zhi
    Zhang, Juan
    Fang, Zhijun
    Huang, Bo
    Jiang, Xiaoyan
    Gao, Yongbin
    Hwang, Jenq-Neng
    IEEE ACCESS, 2019, 7 : 25016 - 25025
  • [29] Inferential Wasserstein generative adversarial networks
    Chen, Yao
    Gao, Qingyi
    Wang, Xiao
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY, 2022, 84 (01) : 83 - 113
  • [30] Single Image Haze Removal Method Using Conditional Random Fields
    Kang, Chunghun
    Kim, Gyeonghwan
    IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (06) : 818 - 822