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
  • [41] Self-supervised Network Evolution for Few-shot Classification
    Tang, Xuwen
    Teng, Zhu
    Zhang, Baopeng
    Fan, Jianping
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 3045 - 3051
  • [42] Single-Image Dehazing Based on Improved Bright Channel Prior and Dark Channel Prior
    Li, Chuan
    Yuan, Changjiu
    Pan, Hongbo
    Yang, Yue
    Wang, Ziyan
    Zhou, Hao
    Xiong, Hailing
    ELECTRONICS, 2023, 12 (02)
  • [43] Dynamic Dark Channel Prior Dehazing with Polarization
    Suo, Haotong
    Guan, Jinge
    Ma, Miao
    Huo, Yongsheng
    Cheng, Yaoyu
    Wei, Naying
    Zhang, Liying
    APPLIED SCIENCES-BASEL, 2023, 13 (18):
  • [44] Dehazing with Dark Channel Prior: Analysis and Implementation
    Lisani, Jose-Luis
    Hessel, Charles
    IMAGE PROCESSING ON LINE, 2024, 14 : 173 - 193
  • [45] A Modified Dark Channel Prior for Improved Dehazing
    Nair, Deepa
    Sankaran, Praveen
    PROCEEDINGS OF THE 2015 IEEE RECENT ADVANCES IN INTELLIGENT COMPUTATIONAL SYSTEMS (RAICS), 2015, : 55 - 59
  • [46] DINO-VITS: Data-Efficient Zero-Shot TTS with Self-Supervised Speaker Verification Loss for Noise Robustness
    Pankov, Vikentii
    Pronina, Valeria
    Kuzmin, Alexander
    Borisov, Maksim
    Usoltsev, Nikita
    Zeng, Xingshan
    Golubkov, Alexander
    Ermolenko, Nikolai
    Shirshova, Aleksandra
    Matveeva, Yulia
    INTERSPEECH 2024, 2024, : 697 - 701
  • [47] Zero-Shot Object Counting With Vision-Language Prior Guidance Network
    Zhai, Wenzhe
    Xing, Xianglei
    Gao, Mingliang
    Li, Qilei
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2025, 35 (03) : 2487 - 2498
  • [48] Few-shot object detection based on self-supervised feature pyramid network
    Lv, Wen
    Qi, Xinwei
    Shi, Hongbo
    Tan, Shuai
    Song, Bing
    Tao, Yang
    JOURNAL OF ELECTRONIC IMAGING, 2024, 33 (02)
  • [49] Generative Zero-shot Network Quantization
    He, Xiangyu
    Lu, Jiahao
    Xu, Weixiang
    Hu, Qinghao
    Wang, Peisong
    Cheng, Jian
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 2994 - 3005
  • [50] Zero-Shot Image Dehazing Using Pseudo Atmospheric Light Image
    Jo, Eunsung
    Park, Eunpil
    Sim, Jae-Young
    2022 IEEE 24TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP), 2022,