DMGINE: Day-Memory Guided Nighttime Image Enhancement for Dynamic Traffic Scenes
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (9) · 7251-7259
DOI: 10.1609/aaai.v40i9.37662 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ruizhou Liu und 4 weiteren Autor:innen.
Abstract (Originalsprache)
We introduce Daytime-Memory Guided Nighttime Image Enhancement (DMGNIE) framework, the first framework that turns long-running daytime surveillance videos of a single intersection into persistent “daytime memory” to guide nighttime image enhancement in traffic scenes. Our key insight is simple yet powerful: for a static scene, perfectly exposed daytime frames are, pixel-for-pixel, high-quality illumination prior for the same location under extreme low-light. Due to the complex lighting conditions in real-world traffic scenes, existing low-light image enhancement (LLIE) methods suffer from issues such as overexposure in highlight regions and noise amplification in low-light condition regions, which degrades the performance of downstream computer vision tasks. DMGNIE tackles these issues in two steps: (1) SegBMN, a semantic prior-based background modeling network, distills a clean, static daytime background from hours of video as scene prior guiding the enhancement of nighttime image; (2) a Foreground Localization-Guided Contrastive Learning module avoid the interference from the background prior with foreground objects during the guidance by maximizing the differences between foreground and background features. Finally, We conduct comprehensive experiments on real traffic surveillance datasets of two cities to evaluate the effectiveness. And the experimental results demonstrate that DMGNIE outperforms state-of-the-art baselines and achieves superior performance in challenging low-light conditions.
Zitieren
APA
Liu, R., Wu, Z., Liu, Z., Zheng, Q., & Huang, Q. (2026). DMGINE: Day-Memory Guided Nighttime Image Enhancement for Dynamic Traffic Scenes. Proceedings of the AAAI Conference on Artificial Intelligence, 40(9), 7251-7259. https://doi.org/10.1609/aaai.v40i9.37662
Vancouver
Liu R, Wu Z, Liu Z, Zheng Q, Huang Q. DMGINE: Day-Memory Guided Nighttime Image Enhancement for Dynamic Traffic Scenes. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(9):7251-7259. doi:10.1609/aaai.v40i9.37662
BibTeX
@article{Liu2026,
author = {Liu, Ruizhou and Wu, Zhe and Liu, Zimo and Zheng, Qingfang and Huang, Qingming},
title = {DMGINE: Day-Memory Guided Nighttime Image Enhancement for Dynamic Traffic Scenes},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {9},
pages = {7251--7259},
doi = {10.1609/aaai.v40i9.37662}
}
EUVIMED