English

TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility

Machine Learning 2026-03-23 v1 Artificial Intelligence

Abstract

High-quality GPS trajectories are essential for location-based web services and smart city applications, including navigation, ride-sharing and delivery. However, due to low sampling rates and limited infrastructure coverage during data collection, real-world trajectories are often sparse and feature unevenly distributed location points. Recovering these trajectories into dense and continuous forms is essential but challenging, given their complex and irregular spatio-temporal patterns. In this paper, we introduce a novel diffusion model for trajectory recovery named TRACE, which reconstruct dense and continuous trajectories from sparse and incomplete inputs. At the core of TRACE, we propose a State Propagation Diffusion Model (SPDM), which integrates a novel memory mechanism, so that during the denoising process, TRACE can retain and leverage intermediate results from previous steps to effectively reconstruct those hard-to-recover trajectory segments. Extensive experiments on multiple real-world datasets show that TRACE outperforms the state-of-the-art, offering >>26\% accuracy improvement without significant inference overhead. Our work strengthens the foundation for mobile and web-connected location services, advancing the quality and fairness of data-driven urban applications. Code is available at: https://github.com/JinmingWang/TRACE

Keywords

Cite

@article{arxiv.2603.19474,
  title  = {TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility},
  author = {Jinming Wang and Hai Wang and Hongkai Wen and Geyong Min and Man Luo},
  journal= {arXiv preprint arXiv:2603.19474},
  year   = {2026}
}

Comments

This article is accepted by WWW 2026, Dubai, United Arab Emirates

R2 v1 2026-07-01T11:29:03.168Z