# Noise Matters: Diffusion Model-based Urban Mobility Generation with Collaborative Noise Priors

arXiv: https://arxiv.org/abs/2412.05000 · HTML: https://mlsanity.com/paper/2412.05000/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 25 of its 68 references that are in the map.
- First posted on arXiv 6 Dec 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2303.08320/) (2023)
- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [A Survey on Deep Learning for Human Mobility](https://mlsanity.com/paper/2012.02825/) (2020)
- [UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction](https://mlsanity.com/paper/2402.11838/) (2024)
- [DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model](https://mlsanity.com/paper/2304.11582/) (2023)
- [Deep Gravity: enhancing mobility flows generation with deep neural networks and geographic information](https://mlsanity.com/paper/2012.00489/) (2020)
- [LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection](https://mlsanity.com/paper/2006.10521/) (2020)
- [Spatio-temporal Diffusion Point Processes](https://mlsanity.com/paper/2305.12403/) (2023)
- [TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models](https://mlsanity.com/paper/2403.17005/) (2024)
- [Learning to Simulate Daily Activities via Modeling Dynamic Human Needs](https://mlsanity.com/paper/2302.10897/) (2023)
- [Trajectory Recovery From Ash: User Privacy Is NOT Preserved in Aggregated Mobility Data](https://mlsanity.com/paper/1702.06270/) (2017)
- [Diffusion Transformers as Open-World Spatiotemporal Foundation Models](https://mlsanity.com/paper/2411.12164/) (2024)
- [Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework](https://mlsanity.com/paper/2410.10524/) (2024)
- [PateGail: A Privacy-Preserving Mobility Trajectory Generator with Imitation Learning](https://mlsanity.com/paper/2407.16729/) (2024)
- [Road Planning for Slums via Deep Reinforcement Learning](https://mlsanity.com/paper/2305.13060/) (2023)
- [UniFlow: A Foundation Model for Unified Urban Spatio-Temporal Flow Prediction](https://mlsanity.com/paper/2411.12972/) (2024)

## Built on by (most cited first, 8 of 8)

- [A Survey of Physics-Informed AI for Complex Urban Systems](https://mlsanity.com/paper/2506.13777/) (2025)
- [Breaking Data Silos: Towards Open and Scalable Mobility Foundation Models via Generative Continual Learning](https://mlsanity.com/paper/2506.06694/) (2025)
- [DiffMove: Group Mobility Tendency Enhanced Trajectory Recovery via Diffusion Model](https://mlsanity.com/paper/2503.18302/) (2025)
- [A Comprehensive Evaluation Framework for Synthetic Trip Data Generation in Public Transport](https://mlsanity.com/paper/2510.24375/) (2025)
- [M-STAR: Multi-Scale Spatiotemporal Autoregression for Human Mobility Modeling](https://mlsanity.com/paper/2512.07314/) (2025)
- [InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories](https://mlsanity.com/paper/2604.04106/) (2026)
- [DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal Semantic Modeling](https://mlsanity.com/paper/2606.09086/) (2026)
- [Encounter-Driven City-Scale Human Mobility Generation with Large Language Models](https://mlsanity.com/paper/2610.17672/) (2026)

## Abstract (arXiv)

With global urbanization, the focus on sustainable cities has largely grown, driving research into equity, resilience, and urban planning, which often relies on mobility data. The rise of web-based apps and mobile devices has provided valuable user data for mobility-related research. However, real-world mobility data is costly and raises privacy concerns. To protect privacy while retaining key features of real-world movement, the demand for synthetic data has steadily increased. Recent advances in diffusion models have shown great potential for mobility trajectory generation due to their ability to model randomness and uncertainty. However, existing approaches often directly apply identically distributed (i.i.d.) noise sampling from image generation techniques, which fail to account for the spatiotemporal correlations and social interactions that shape urban mobility patterns. In this paper, we propose CoDiffMob, a diffusion model for urban mobility generation with collaborative noise priors, we emphasize the critical role of noise in diffusion models for generating mobility data. By leveraging both individual movement characteristics and population-wide dynamics, we construct novel collaborative noise priors that provide richer and more informative guidance throughout the generation process. Extensive experiments demonstrate the superiority of our method, with generated data accurately capturing both individual preferences and collective patterns, achieving an improvement of over 32%. Furthermore, it can effectively replace web-derived mobility data to better support downstream applications, while safeguarding user privacy and fostering a more secure and ethical web. This highlights its tremendous potential for applications in sustainable city-related research. The code and data are available at https://github.com/tsinghua-fib-lab/CoDiffMob.