EUVIMEDEUVIMED entdecken
Crossref

Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training

Yunwei Lan, Zhigao Cui, Chang Liu, Jialun Peng, Nian Wang, Xin Luo, Dong Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 4455-4463

DOI: 10.1609/aaai.v39i4.32469 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yunwei Lan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 49-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous studies have been proposed, current methods demonstrate limited generalization for various real scenes due to limited feature representation and insufficient use of real-world prior. Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing, and propose an unpaired framework named Diff-Dehazer. Specifically, we leverage diffusion prior as bijective mapping learners within the CycleGAN, a classic unpaired learning framework. Considering that physical priors contain pivotal statistics information of real-world data, we further excavate real-world knowledge by integrating physical priors into our framework. Furthermore, we introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities, so as to improve the dehazing effect. Extensive experiments on multiple real-world datasets demonstrate the superior performance of our method.

Zitieren

APA

Lan, Y., Cui, Z., Liu, C., Peng, J., Wang, N., Luo, X., & Liu, D. (2025). Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 4455-4463. https://doi.org/10.1609/aaai.v39i4.32469

Vancouver

Lan Y, Cui Z, Liu C, Peng J, Wang N, Luo X, et al. Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):4455-4463. doi:10.1609/aaai.v39i4.32469

BibTeX
@article{Lan2025,
  author = {Lan, Yunwei and Cui, Zhigao and Liu, Chang and Peng, Jialun and Wang, Nian and Luo, Xin and Liu, Dong},
  title = {Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {4},
  pages = {4455--4463},
  doi = {10.1609/aaai.v39i4.32469}
}
Kostenlos starten →