Huang, Jung-HaoLai, Bo-YunWong, Sai-KeungLin, Wen-ChiehChristie, MarcHan, Ping-HsuanLin, Shih-SyunPietroni, NicoSchneider, TeseoTsai, Hsin-RueyWang, Yu-ShuenZhang, Eugene2025-10-072025-10-072025978-3-03868-295-0https://doi.org/10.2312/pg.20251262https://diglib.eg.org/handle/10.2312/pg20251262This paper presents a two-stage optimization method for traffic reconstruction that considers both microscopic and macroscopic features. The method employs a microscopic driving model and uses the average speeds in the lanes as a macroscopic metric to reconstruct traffic that balances the characteristics of traffic flow and vehicle behaviors. Our results on the NGSIM dataset, conducted primarily on straight road segments, demonstrate that the proposed method effectively balances the preservation of microscopic-level details with the simulation of macroscopic traffic flows. Both stages of our method outperform previous work in their respective domains. Furthermore, animated results rendered in the CARLA simulator highlight the realism of the generated driving behaviors, underscoring the model's ability to accurately reproduce various scenarios observed in real-world traffic. By recovering physical simulation parameters from real data, our framework can be utilized to generate diverse, realistic traffic flows, supporting applications such as traffic animation, data augmentation, system testing, and traffic behavior analysis.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Procedural animation; Interactive simulationComputing methodologies → Procedural animationInteractive simulation10.2312/pg.2025126211 pages