Low-Light Image Enhancement via Multi-Exposure Progressive Contrastive Regularization
IEEE Transactions on Circuits and Systems for Video Technology · 2025-12 · 35 (12) · 11978-11992
DOI: 10.1109/tcsvt.2025.3589217 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-12. Verfasst von Zuojie Xie und 9 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: Intelligent Enhancement Technology for Night Scene Research Fund.
Abstract (Originalsprache)
Low-light image enhancement (LLIE) aims to restore low-light images to their normal-light counterparts with optimal global illumination distribution and clear local details. With the advancement of deep learning, deep learning-based methods have become the mainstream in the LLIE community. However, most deep learning-based method cannot yet fully exploit the global and local contextual information in the low-light image. In this paper, we introduce a dual-branch module to simultaneously restore global and local features from spatial and frequency domain. To fuse these multi-level features, we propose a perception module to perform feature interaction between global and local features via cross attention and self-gating. By integrating the two developed modules into a U-Net backbone, we present a global-local interaction network for LLIE. Furthermore, recent studies have shown that contrastive learning can be an effective paradigm for the LLIE task. However, previous works typically use semantically-inconsistent under-/over-exposed images as negative samples. These images are very dissimilar to the ground-truth and cannot provide sufficient regularization in contrastive learning. To address this limitation, we explore a practical multi-exposure progressive contrastive regularization framework for LLIE. With a customized sample generation, sample selection, and progressive learning strategy, our proposed framework progressively narrows down the solution space around the optimum, and helps to improve the performance of LLIE methods without additional inference overhead. Combining the proposed network and contrastive regularization, our proposed method achieves favorable results compared to state-of-the-art LLIE methods on benchmark datasets. Extensive experiments further demonstrate the generalization ability of our proposed method.
Förderung
- Intelligent Enhancement Technology for Night Scene Research Fund
Zitieren
APA
Xie, Z., Ren, H., Huang, J., He, Z., Lu, H., Liu, Y., Lu, J., Yuan, L., Liu, S., & Xie, C. (2025). Low-Light Image Enhancement via Multi-Exposure Progressive Contrastive Regularization. IEEE Transactions on Circuits and Systems for Video Technology, 35(12), 11978-11992. https://doi.org/10.1109/tcsvt.2025.3589217
Vancouver
Xie Z, Ren H, Huang J, He Z, Lu H, Liu Y, et al. Low-Light Image Enhancement via Multi-Exposure Progressive Contrastive Regularization. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(12):11978-11992. doi:10.1109/tcsvt.2025.3589217
BibTeX
@article{Xie2025,
author = {Xie, Zuojie and Ren, Hao and Huang, Junjian and He, Zhiquan and Lu, Hong and Liu, Yong and Lu, Jiawen and Yuan, Lvfan and Liu, Shulin and Xie, Changyong},
title = {Low-Light Image Enhancement via Multi-Exposure Progressive Contrastive Regularization},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {12},
pages = {11978--11992},
doi = {10.1109/tcsvt.2025.3589217}
}
EUVIMED