Night-to-Day Translation via Illumination Degradation Disentanglement

作者：Guanzhou Lan, Yuqi Yang, Zhigang Wang, Dong Wang, Xuelong Li, Bin Zhao · 发表于：IEEE Transactions on Multimedia · 年份：2026 · DOI：10.1109/tmm.2026.3700823 · 被引用次数：1 · 研究领域：Color Science and Applications

Night-to-Day translation (Night2Day) aims to achieve day-like vision for nighttime scenes. However, processing night images with complex degradations remains a significant challenge under unpaired conditions. Previous methods that uniformly mitigate these degradations have proven inadequate in simultaneously restoring daytime domain information and preserving underlying semantics. In this paper, we proposeN2D3(Night-to-Day viaDegradationDisentanglement) to identify different degradation patterns in nighttime images. Specifically, our method comprises a degradation disentanglement module and a degradation-aware contrastive learning module. Firstly, we extract physical priors from a photometric model based on Kubelka-Munk theory. Then, guided by these physical priors, we design a disentanglement module to discriminate among different illumination degradation regions. Finally, we introduce the degradation-aware contrastive learning strategy to preserve semantic consistency across distinct degradation regions. Our method is evaluated on two public datasets, demonstrating a significant improvement in visual quality and considerable potential for benefiting downstream tasks.