EUVIMEDEUVIMED entdecken
Crossref

Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement

Wenhui Wu, Jian Weng, Pingping Zhang, Xu Wang, Wenhan Yang, Jianmin Jiang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-04 · 47 (4) · 2545-2562

DOI: 10.1109/tpami.2024.3524538 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-04. Verfasst von Wenhui Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Guangdong Provincial Key Laboratory.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retinex model-based methods have shown to be effective in layer-wise manipulation with well-designed priors for low-light image enhancement (LLIE). However, the hand-crafted priors and conventional optimization algorithm adopted to solve the layer decomposition problem result in the lack of adaptivity and efficiency. To this end, this paper proposes a Retinex-based deep unfolding network (URetinex-Net++), which unfolds an optimization problem into a learnable network to decompose a low-light image into reflectance and illumination layers. By formulating the decomposition problem as an implicit priors regularized model, three learning-based modules are carefully designed, responsible for data-dependent initialization, high-efficient unfolding optimization, and fairly-flexible component adjustment, respectively. Particularly, the proposed unfolding optimization module, introducing two networks to adaptively fit implicit priors in the data-driven manner, can realize noise suppression and details preservation for decomposed components. URetinex-Net++ is a further augmented version of URetinex-Net, which introduces a cross-stage fusion block to alleviate the color defect in URetinex-Net. Therefore, boosted performance on LLIE can be obtained in both visual quality and quantitative metrics, where only a few parameters are introduced and little time is cost. Extensive experiments on real-world low-light images qualitatively and quantitatively demonstrate the effectiveness and superiority of the proposed URetinex-Net++ over state-of-the-art methods.

Förderung

  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Guangdong Provincial Key Laboratory

Zitieren

APA

Wu, W., Weng, J., Zhang, P., Wang, X., Yang, W., & Jiang, J. (2025). Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4), 2545-2562. https://doi.org/10.1109/tpami.2024.3524538

Vancouver

Wu W, Weng J, Zhang P, Wang X, Yang W, Jiang J. Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(4):2545-2562. doi:10.1109/tpami.2024.3524538

BibTeX
@article{Wu2025,
  author = {Wu, Wenhui and Weng, Jian and Zhang, Pingping and Wang, Xu and Yang, Wenhan and Jiang, Jianmin},
  title = {Interpretable Optimization-Inspired Unfolding Network for Low-Light Image Enhancement},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {4},
  pages = {2545--2562},
  doi = {10.1109/tpami.2024.3524538}
}
Kostenlos starten →