EUVIMEDEUVIMED entdecken
Crossref

Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement

Kai Shang, Mingwen Shao, Chao Wang, Yuanshuo Cheng, Shuigen Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4722-4730

DOI: 10.1609/aaai.v38i5.28273 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Kai Shang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffusion models have achieved remarkable progress in low-light image enhancement. However, there remain two practical limitations: (1) existing methods mainly focus on the spatial domain for the diffusion process, while neglecting the essential features in the frequency domain; (2) conventional patch-based sampling strategy inevitably leads to severe checkerboard artifacts due to the uneven overlapping. To address these limitations in one go, we propose a Multi-Domain Multi-Scale (MDMS) diffusion model for low-light image enhancement. In particular, we introduce a spatial-frequency fusion module to seamlessly integrates spatial and frequency information. By leveraging the Multi-Domain Learning (MDL) paradigm, our proposed model is endowed with the capability to adaptively facilitate noise distribution learning, thereby enhancing the quality of the generated images. Meanwhile, we propose a Multi-Scale Sampling (MSS) strategy that follows a divide-ensemble manner by merging the restored patches under different resolutions. Such a multi-scale learning paradigm explicitly derives patch information from different granularities, thus leading to smoother boundaries. Furthermore, we empirically adopt the Bright Channel Prior (BCP) which indicates natural statistical regularity as an additional restoration guidance. Experimental results on LOL and LOLv2 datasets demonstrate that our method achieves state-of-the-art performance for the low-light image enhancement task. Codes are available at https://github.com/Oliiveralien/MDMS.

Zitieren

APA

Shang, K., Shao, M., Wang, C., Cheng, Y., & Wang, S. (2024). Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4722-4730. https://doi.org/10.1609/aaai.v38i5.28273

Vancouver

Shang K, Shao M, Wang C, Cheng Y, Wang S. Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4722-4730. doi:10.1609/aaai.v38i5.28273

BibTeX
@article{Shang2024,
  author = {Shang, Kai and Shao, Mingwen and Wang, Chao and Cheng, Yuanshuo and Wang, Shuigen},
  title = {Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4722--4730},
  doi = {10.1609/aaai.v38i5.28273}
}
Kostenlos starten →