EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Zero-shot trajectory generation with self-supervised diffusion model

TongHao Liu, JiaoLing Zheng

Computational Urban Science · 10.08.2026 · 6 (1)

DOI: 10.1007/s43762-026-00280-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Urban Science, online erschienen am 10.08.2026. Verfasst von TongHao Liu und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation of Sichuan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vehicle trajectory data play a crucial role in modern intelligent transportation systems. Traditional generative models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), often struggle to accurately capture the distributional characteristics of trajectories in real-world scenarios. Moreover, conventional traffic trajectory generation methods face challenges due to their reliance on real-world road network data that are difficult to acquire and have limited availability. To address these issues, this study leverages the inherent correlation between surveillance camera data and vehicle trajectories, developing a zero-shot trajectory generation method (defined as generating valid trajectories without any complete single-vehicle trajectory annotations, only using aggregated traffic flow statistics and road network topology) based on a diffusion model. We treat surveillance traffic flow distributions as conditioning information to guide the denoising process continuously, employing an adaptive optimization framework to generate compliant and high-quality trajectories. All experiments are validated on real-world traffic datasets from Dadukou District, Chongqing. Notably, the entire model training process does not use any complete single-vehicle trajectory annotations, relying only on aggregated traffic flow statistics and public road network topology. Using surveillance traffic flow data as input, the generated synthetic trajectories not only align closely with real trajectories but also demonstrate comparable effectiveness. Extensive experiments validate the efficacy of the proposed method in zero-shot trajectory generation tasks, showing excellent performance in both trajectory similarity and distributional similarity.

Förderung

  • Natural Science Foundation of Sichuan Province

Zitieren

APA

Liu, T., & Zheng, J. (2026). Zero-shot trajectory generation with self-supervised diffusion model. Computational Urban Science, 6(1). https://doi.org/10.1007/s43762-026-00280-7

Vancouver

Liu T, Zheng J. Zero-shot trajectory generation with self-supervised diffusion model. Computational Urban Science. 2026;6(1). doi:10.1007/s43762-026-00280-7

BibTeX
@article{Liu2026,
  author = {Liu, TongHao and Zheng, JiaoLing},
  title = {Zero-shot trajectory generation with self-supervised diffusion model},
  journal = {Computational Urban Science},
  year = {2026},
  volume = {6},
  number = {1},
  doi = {10.1007/s43762-026-00280-7}
}
Kostenlos starten →