Supplementary data for the paper "Deep Learning Approach for Realistic Traffic Video Changes Across Lighting and Weather Conditions"

Recent advances in GAN-based architectures have led to innovative methods for image transformation. The lack of diversity of environmental factors, such as lighting conditions and seasons in public data, prevents researchers from effectively studying the differences in the behaviour of road users under varying conditions. This study introduces a deep learning pipeline that combines CycleGAN-turbo and Real-ESRGAN to improve video transformations of traffic scenes. Evaluated using dashcam videos from Los Angeles, London, and Hong Kong, our pipeline demonstrates a notable improvement in T-SIMM for temporal consistency during night-to-day transformations, achieving a 7.97% increase for Hong Kong, 7.35% for Los Angeles, and 3.41% for London compared to CycleGAN-turbo. PSNR and VPQ scores are comparable, but the pipeline performs better in DINO structure similarity and KL divergence, with up to 153.49% better structural fidelity in Hong Kong compared to Pix2Pix and 107.32% better compared to ToDayGAN. This approach demonstrates better realism and temporal coherence in day-to-night, night-to-day, and clear-to-rainy transitions.

近年来，基于生成对抗网络（Generative Adversarial Network，GAN）的架构研究取得显著进展，催生了诸多用于图像转换的创新方法。公开数据集内环境因素（如光照条件、季节）缺乏多样性，导致研究者难以有效探究不同环境下道路使用者行为模式的差异。本研究提出一种结合CycleGAN-turbo与Real-ESRGAN的深度学习流水线，用于优化交通场景的视频转换任务。本研究使用来自洛杉矶、伦敦与香港的行车记录仪视频对该流水线进行评估，结果显示，在夜昼转换任务中，其在衡量时序一致性的T-SIMM指标上实现了显著提升：相较于CycleGAN-turbo，香港数据集上的提升幅度达7.97%，洛杉矶为7.35%，伦敦为3.41%。该方法的峰值信噪比（Peak Signal-to-Noise Ratio, PSNR）与视频感知质量（Visual Perceptual Quality, VPQ）得分与基准方法相当，但在DINO结构相似度与KL散度（Kullback-Leibler divergence, KL）指标上表现更优：相较于Pix2Pix，香港数据集上的结构保真度提升最高可达153.49%，相较于ToDayGAN则提升107.32%。该方法在昼夜转换、夜昼转换以及晴雨转换任务中，均展现出更优的视觉真实性与时序一致性。