mlsanityData to 14 Oct 2026

TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility

arXiv 2603.19474 ↗First posted 19 Mar 2026cs.LG cs.AIcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 12 of its 26 references that are in the map. First posted on arXiv 19 Mar 2026.

Builds on

12 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model23 Apr

Other references · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  7. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  8. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  9. 2023PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputationcited by 66
  10. 2023Continuous Trajectory Generation Based on Two-Stage GANcited by 37
  11. 2024Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generationcited by 29

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024TrajWeaver: Trajectory Recovery with State Propagation Diffusion Model
  2. 2026TrajFlow: Nation-wide Pseudo GPS Trajectory Generation with Flow Matching Models
  3. 2024Map2Traj: Street Map Piloted Zero-shot Trajectory Generation with Diffusion Model
  4. 2026TrajDLM: Topology-Aware Block Diffusion Language Model for Trajectory Generation
  5. 2023DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model
  6. 2025DiffMove: Group Mobility Tendency Enhanced Trajectory Recovery via Diffusion Model
  7. 2026Coarse-to-Fine Multi-Resolution Diffusion Models for Trajectory Generation in Urban Systems
  8. 2025Leveraging the Spatial Hierarchy: Coarse-to-fine Trajectory Generation via Cascaded Hybrid Diffusion