JTE-CFlow for Low-Light Enhancement and Zero-Element Pixels Restoration With Application to Night Traffic Monitoring Images
IEEE Transactions on Intelligent Transportation Systems · 2025-03 · 26 (3) · 3755-3770
DOI: 10.1109/tits.2024.3510832 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2025-03. Verfasst von Changhui Hu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Nanjing University of Posts and Telecommunications.
Abstract (Originalsprache)
We observe that the low-light RGB images, as well as night traffic monitoring (NTM) images, contain lots of color pixels with zeros caused by the low-light, which means that the low-light images suffer both information weakness and information loss of zero-element pixels. In this paper, we propose a novel flow-based generative method JTE-CFlow for low-light image enhancement, which consists of a joint-attention transformer based conditional encoder (JTE) and a map-wise cross affine coupling flow (CFlow). Specifically, JTE executes short-range and long-range operations by RRDBs (i.e., residual-in-residual dense blocks) and JATs (i.e., joint-attention transformer blocks) in series connection. JAT achieves weak information amplification and information loss restoration of zero-element pixels by the integration of self-attention and specific-attention with sharing the same value vectors, where the query and key vectors of specific-attention are from the zero-map feature of the low-light image. On the other hand, CFlow develops a map-wise cross affine coupling (MCAC) layer to perform cross learning for the flow feature, and a multiplication coupling network (MCN) to learn the transformation parameters of MCAC. JTE-CFlow learns to map the subtraction of outputs of CFlow and JTE (i.e., the residual code) into a standard normal distribution, and the inverse network of CFlow takes the latent feature of the low-light image as its input to infer the enhanced image. Experiments show that JTE-CFlow outperforms most SOTA methods on 7 mainstream low-light datasets with the same architecture, and can be applied to enhance NTM images. The source code and pre-trained models are available at https://github.com/NJUPT-IPR-HuYin/JTE-CFlow.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Nanjing University of Posts and Telecommunications
Zitieren
APA
Hu, C., Hu, Y., Xu, L., Guo, Y., Cai, Z., Jing, X., & Liu, P. (2025). JTE-CFlow for Low-Light Enhancement and Zero-Element Pixels Restoration With Application to Night Traffic Monitoring Images. IEEE Transactions on Intelligent Transportation Systems, 26(3), 3755-3770. https://doi.org/10.1109/tits.2024.3510832
Vancouver
Hu C, Hu Y, Xu L, Guo Y, Cai Z, Jing X, et al. JTE-CFlow for Low-Light Enhancement and Zero-Element Pixels Restoration With Application to Night Traffic Monitoring Images. IEEE Transactions on Intelligent Transportation Systems. 2025;26(3):3755-3770. doi:10.1109/tits.2024.3510832
BibTeX
@article{Hu2025,
author = {Hu, Changhui and Hu, Yin and Xu, Lintao and Guo, Yanyong and Cai, Ziyun and Jing, Xiaoyuan and Liu, Pan},
title = {JTE-CFlow for Low-Light Enhancement and Zero-Element Pixels Restoration With Application to Night Traffic Monitoring Images},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2025},
volume = {26},
number = {3},
pages = {3755--3770},
doi = {10.1109/tits.2024.3510832}
}
EUVIMED