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 LiuIEEE TPAMI 2025 · OpenReview

Abstract

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.
BibTeX
@article{ma2025learning,
  author = {Long Ma and Tengyu Ma and Chengpei Xu and Jinyuan Liu and Xin Fan and Zhongxuan Luo and Risheng Liu},
  title = {{Learning With Self-Calibrator for Fast and Robust Low-Light Image Enhancement}},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  url = {https://openreview.net/forum?id=WEXIb6wXuA},
}

Loading related content...

Figure