Self-supervised zero-shot dehazing network based on dark channel prior

被引:4
|
作者
Xiao, Xinjie [1 ]
Ren, Yuanhong [2 ]
Li, Zhiwei [1 ]
Zhang, Nannan [1 ]
Zhou, Wuneng [2 ]
机构
[1] Shanghai Univ Engn Sci, Sch Elect & Elect Engn, Shanghai 201620, Peoples R China
[2] Donghua Univ, Coll Informat Sci & Technol, Shanghai 201620, Peoples R China
基金
中国国家自然科学基金;
关键词
Image dehazing; Quad-tree algorithm; Self-supervised; Zero-shot; IMAGE; WEATHER;
D O I
10.1007/s12200-023-00062-7
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
Most learning-based methods previously used in image dehazing employ a supervised learning strategy, which is time-consuming and requires a large-scale dataset. However, large-scale datasets are difficult to obtain. Here, we propose a self-supervised zero-shot dehazing network (SZDNet) based on dark channel prior, which uses a hazy image generated from the output dehazed image as a pseudo-label to supervise the optimization process of the network. Additionally, we use a novel multichannel quad-tree algorithm to estimate atmospheric light values, which is more accurate than previous methods. Furthermore, the sum of the cosine distance and the mean squared error between the pseudo-label and the input image is applied as a loss function to enhance the quality of the dehazed image. The most significant advantage of the SZDNet is that it does not require a large dataset for training before performing the dehazing task. Extensive testing shows promising performances of the proposed method in both qualitative and quantitative evaluations when compared with state-of-the-art methods.
引用
收藏
页数:14
相关论文
共 50 条
  • [31] Zero-Shot Self-Supervised Joint Temporal Image and Sensitivity Map Reconstruction via Linear Latent Space
    Zhang, Molin
    Xu, Junshen
    Arefeen, Yamin
    Adalsteinsson, Elfar
    MEDICAL IMAGING WITH DEEP LEARNING, VOL 227, 2023, 227 : 1713 - 1725
  • [32] ZMM-TTS: Zero-Shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-Supervised Discrete Speech Representations
    Gong, Cheng
    Wang, Xin
    Cooper, Erica
    Wells, Dan
    Wang, Longbiao
    Dang, Jianwu
    Richmond, Korin
    Yamagishi, Junichi
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2024, 32 : 4036 - 4051
  • [33] Self-supervised Multimodal Generalized Zero Shot Learning for Gleason Grading
    Mahapatra, Dwarikanath
    Bozorgtabar, Behzad
    Kuanar, Shiba
    Ge, Zongyuan
    DOMAIN ADAPTATION AND REPRESENTATION TRANSFER, AND AFFORDABLE HEALTHCARE AND AI FOR RESOURCE DIVERSE GLOBAL HEALTH (DART 2021), 2021, 12968 : 46 - 56
  • [34] A review on dark channel prior based image dehazing algorithms
    Lee, Sungmin
    Yun, Seokmin
    Nam, Ju-Hun
    Won, Chee Sun
    Jung, Seung-Won
    EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2016, : 1 - 23
  • [35] Optimized fast dehazing method based on dark channel prior
    Chu, Hong-Li
    Li, Yuan-Xiang
    Zhou, Ze-Ming
    Shen, Ji
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2013, 41 (04): : 791 - 797
  • [36] A review on dark channel prior based image dehazing algorithms
    Sungmin Lee
    Seokmin Yun
    Ju-Hun Nam
    Chee Sun Won
    Seung-Won Jung
    EURASIP Journal on Image and Video Processing, 2016
  • [37] Study On Image Dehazing Methods Based On Dark Channel Prior
    Guo Han
    Xu Xiaoting
    Li Bo
    ACTA OPTICA SINICA, 2018, 38 (04)
  • [38] Adaptive Tolerance Dehazing Algorithm Based on Dark Channel Prior
    Yang, Fan
    Tang, ShouLian
    ALGORITHMS, 2020, 13 (02)
  • [39] An Improved Image Dehazing Algorithm Based on Dark Channel Prior
    Liu, Jiajie
    Zheng, Jieying
    Cui, Ziguan
    Tang, Guijin
    Liu, Feng
    PROCEEDINGS OF 2014 IEEE WORKSHOP ON ADVANCED RESEARCH AND TECHNOLOGY IN INDUSTRY APPLICATIONS (WARTIA), 2014, : 1401 - 1404
  • [40] An Adaptive Image Dehazing Algorithm based on Dark Channel Prior
    Chen, Chunlin
    Li, Jiatong
    Deng, Sibin
    Li, Feng
    Ling, Qiang
    2017 29TH CHINESE CONTROL AND DECISION CONFERENCE (CCDC), 2017, : 7472 - 7477