EUVIMEDEUVIMED entdecken
Crossref

Learning With Self-Calibrator for Fast and Robust Low-Light Image Enhancement

Long Ma, Tengyu Ma, Chengpei Xu, Jinyuan Liu, Xin Fan, Zhongxuan Luo, Risheng Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-10 · 47 (10) · 9095-9112

DOI: 10.1109/tpami.2025.3586712 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-10. Verfasst von Long Ma und 6 weiteren Autor:innen. Die Arbeit wurde bisher 51-mal zitiert (Crossref) und nennt 77 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Central Guidance for Local Science and Technology Development Fund, Distinguished Young Scholars Funds of Dalian.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional Neural Networks (CNNs) have shown significant success in the low-light image enhancement task. However, most of existing works encounter challenges in balancing quality and efficiency simultaneously. This limitation hinders practical applicability in real-world scenarios and downstream vision tasks. To overcome these obstacles, we propose a Self-Calibrated Illumination (SCI) learning scheme, introducing a new perspective to boost the model's capability. Based on a weight-sharing illumination estimation process, we construct an embedded self-calibrator to accelerate stage-level convergence, yielding gains that utilize only a single basic block for inference, which drastically diminishes computation cost. Additionally, by introducing the additivity condition on the basic block, we acquire a reinforced version dubbed SCI++, which disentangles the relationship between the self-calibrator and illumination estimator, providing a more interpretable and effective learning paradigm with faster convergence and better stability. We assess the proposed enhancers on standard benchmarks and in-the-wild datasets, confirming that they can restore clean images from diverse scenes with higher quality and efficiency. The verification on different levels of low-light vision tasks shows our applicability against other methods.

Förderung

  • National Natural Science Foundation of China
  • Central Guidance for Local Science and Technology Development Fund
  • Distinguished Young Scholars Funds of Dalian
  • China Postdoctoral Science Foundation
  • Postdoctoral Fellowship Program of CPSF
  • Dalian Science and Technology Innovation Fund-Young Tech Star
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Ma, L., Ma, T., Xu, C., Liu, J., Fan, X., Luo, Z., & Liu, R. (2025). Learning With Self-Calibrator for Fast and Robust Low-Light Image Enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(10), 9095-9112. https://doi.org/10.1109/tpami.2025.3586712

Vancouver

Ma L, Ma T, Xu C, Liu J, Fan X, Luo Z, et al. Learning With Self-Calibrator for Fast and Robust Low-Light Image Enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(10):9095-9112. doi:10.1109/tpami.2025.3586712

BibTeX
@article{Ma2025,
  author = {Ma, Long and Ma, Tengyu and Xu, Chengpei and Liu, Jinyuan and Fan, Xin and Luo, Zhongxuan and Liu, Risheng},
  title = {Learning With Self-Calibrator for Fast and Robust Low-Light Image Enhancement},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {10},
  pages = {9095--9112},
  doi = {10.1109/tpami.2025.3586712}
}
Kostenlos starten →