Image dehazing is a common operation in autonomous driving, traffic monitoring and surveillance. Learning-based image dehazing has achieved excellent performance recently. However, it is nearly impossible to capture pairs of hazy/clean images from the real world to train an image dehazing network. Most of existing dehazing models that are learnt from synthetically generated hazy images generalize poorly on real-world hazy scenarios due to the obvious domain shift. To deal with this unpaired problem arisen by real-world hazy images, we present Cycle Spectral Normalized Soft likelihood estimation Patch Generative Adversarial Network (Cycle-SNSPGAN) for image dehazing. Cycle-SNSPGAN is an unsupervised dehazing framework to boost the generalization ability on real-world hazy images. To leverage unpaired samples of real-world hazy images without relying on their clean counterparts, we design an SN-Soft-Patch GAN and exploit a new cyclic self-perceptual loss which avoids using the ground-truth image to compute the perceptual similarity. Moreover, a significant color loss is adopted to brighten the dehazed images as human expects. Both visual and numerical results show clear improvements of the proposed Cycle-SNSPGAN over state-of-the-arts in terms of hazy-robustness and image detail recovery, with even only a small dataset training our Cycle-SNSPGAN. Code has been available at https://github.com/yz-wang/Cycle-SNSPGAN.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Cycle-SNSPGAN: Towards Real-World Image Dehazing via Cycle Spectral Normalized Soft Likelihood Estimation Patch GAN


    Beteiligte:
    Wang, Yongzhen (Autor:in) / Yan, Xuefeng (Autor:in) / Guan, Donghai (Autor:in) / Wei, Mingqiang (Autor:in) / Chen, Yiping (Autor:in) / Zhang, Xiao-Ping (Autor:in) / Li, Jonathan (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022-11-01


    Format / Umfang :

    4852327 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Overwater Image Dehazing via Cycle-Consistent Generative Adversarial Network

    Zheng, Shunyuan / Sun, Jiamin / Liu, Qinglin et al. | British Library Conference Proceedings | 2021


    Single-Image Dehazing

    Tian, Jiandong | Springer Verlag | 2021


    Unified Density-Aware Image Dehazing and Object Detection in Real-World Hazy Scenes

    Zhang, Zhengxi / Zhao, Liang / Liu, Yunan et al. | British Library Conference Proceedings | 2021


    Single Image Dehazing via Image Generating

    Zhang, Shengdong / Yao, Jian / Garcia, Edel B. | British Library Conference Proceedings | 2018


    DAY/NIGHT UNCONSTRAINED IMAGE DEHAZING

    Santra, Sanchayan / Chanda, Bhabatosh | British Library Conference Proceedings | 2016