EUVIMEDEUVIMED entdecken
Crossref

You Only Need Clear Images: Self-Supervised Single Image Dehazing

Jiyou Chen, Wenqi Ren, Huihuang Zhao, Qunbing Xia, Gaobo Yang

IEEE Transactions on Multimedia · 2025 · 27 · 5800-5814

DOI: 10.1109/tmm.2025.3542999 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Multimedia, 2025. Verfasst von Jiyou Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Scientific Research Fund of Hunan Provincial Education Department, 14th Five-Year PlanKeyDisciplines andApplication-oriented Special Disciplines of Hunan Province. Xiang, Jiaotong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image hazing refers to adding haze to a clear image, which is important for improving the data amount and diversity of synthetic hazy images that are required to train deep image dehazing models. However, existing image hazing works generate hazy images from a given clear image with a single transmission map. This violates the fact that hazy images are diverse for a natural scene at different times. The domain shift issue between synthetic and real-world hazy images constrains the robustness of deep dehazing models when dealing with real-world hazy images. In this work, we propose an unsupervised haze generation work to synthesize multiple hazy images with diverse haze distributions from a clear image, which requires only an atmospheric scattering model without extra labeling information. Instead of estimating a transmission map from a clear image, we propose to customize the transmission maps by redefining the transmission function. In such a controllable way, hazy images with diverse haze distributions are generated, which avoids the labor-intensive collection of paired data and alleviates the common domain-shift issue of deep image dehazing. Incorporating the unsupervised hazy images generator, we also construct a generalizable self-supervised image dehazing (SSID) framework, where deep image dehazing models can be trained without any human annotations. Extensive experiments on real-world hazy images show that the proposed approach is superior to state-of-the-art unsupervised dehazing works, and achieves competitive performance with the supervised works. Moreover, the proposed SSID framework can be easily generalized to the existing deep dehazing models, greatly improving dehazing robustness on real-world hazy images.

Förderung

  • National Natural Science Foundation of China
  • Scientific Research Fund of Hunan Provincial Education Department
  • 14th Five-Year PlanKeyDisciplines andApplication-oriented Special Disciplines of Hunan Province. Xiang, Jiaotong

Zitieren

APA

Chen, J., Ren, W., Zhao, H., Xia, Q., & Yang, G. (2025). You Only Need Clear Images: Self-Supervised Single Image Dehazing. IEEE Transactions on Multimedia, 27, 5800-5814. https://doi.org/10.1109/tmm.2025.3542999

Vancouver

Chen J, Ren W, Zhao H, Xia Q, Yang G. You Only Need Clear Images: Self-Supervised Single Image Dehazing. IEEE Transactions on Multimedia. 2025;27:5800-5814. doi:10.1109/tmm.2025.3542999

BibTeX
@article{Chen2025,
  author = {Chen, Jiyou and Ren, Wenqi and Zhao, Huihuang and Xia, Qunbing and Yang, Gaobo},
  title = {You Only Need Clear Images: Self-Supervised Single Image Dehazing},
  journal = {IEEE Transactions on Multimedia},
  year = {2025},
  volume = {27},
  pages = {5800--5814},
  doi = {10.1109/tmm.2025.3542999}
}
Kostenlos starten →