# A Road-Conditioned Traffic Movie Prediction Network with Spatiotemporal and Structure-Consistent Learning

arXiv: https://arxiv.org/abs/2605.27884 · HTML: https://mlsanity.com/paper/2605.27884/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 59 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 17 of 17)

- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting](https://mlsanity.com/paper/2012.09641/) (2020)
- [Graph Neural Controlled Differential Equations for Traffic Forecasting](https://mlsanity.com/paper/2112.03558/) (2021)
- [Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting](https://mlsanity.com/paper/2206.09112/) (2022)
- [Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes](https://mlsanity.com/paper/2203.17070/) (2022)
- [Utilizing UNet for the future traffic map prediction task Traffic4cast challenge 2020](https://mlsanity.com/paper/2012.00125/) (2020)
- [Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)](https://mlsanity.com/paper/2305.05237/) (2023)
- [Traffic4cast-Traffic Map Movie Forecasting -- Team MIE-Lab](https://mlsanity.com/paper/1910.13824/) (2019)
- [Learning to Transfer for Traffic Forecasting via Multi-task Learning](https://mlsanity.com/paper/2111.15542/) (2021)
- [Integrating Travel Behavior Forecasting and Generative Modeling for Predicting Future Urban Mobility and Spatial Transformations](https://mlsanity.com/paper/2503.21158/) (2025)
- [A Graph-based U-Net Model for Predicting Traffic in unseen Cities](https://mlsanity.com/paper/2202.06725/) (2022)
- [Traffic Forecasting on Traffic Moving Snippets](https://mlsanity.com/paper/2110.14383/) (2021)
- [Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNet](https://mlsanity.com/paper/2111.05990/) (2021)
- [SwinUNet3D -- A Hierarchical Architecture for Deep Traffic Prediction using Shifted Window Transformers](https://mlsanity.com/paper/2201.06390/) (2022)
- [Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors](https://mlsanity.com/paper/2303.07758/) (2023)
- [Dual Encoding U-Net for Spatio-Temporal Domain Shift Frame Prediction](https://mlsanity.com/paper/2110.11140/) (2021)
- [Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation](https://mlsanity.com/paper/2111.03421/) (2021)

## Abstract (arXiv)

City-wide traffic forecasting is important for congestion management, route guidance, and intelligent transportation systems, but accurate prediction remains challenging when future traffic must be generated as spatial maps over an entire urban network. Existing traffic movie prediction methods have improved frame-level accuracy, yet many still treat forecasting mainly as image reconstruction. This can produce traffic maps that are numerically close to the ground truth but weakly constrained by road layout, connectivity, travel direction, and congestion propagation, especially in cross-city settings where both traffic behavior and road structure change. To address this limitation, this study proposes RCSNet, a road-conditioned spatiotemporal network that reformulates traffic movie prediction as topology-guided future-state generation. RCSNet extracts road-aware representations from static road maps, models multi-horizon traffic dynamics from historical observations, aligns directional traffic features with local road structure, and progressively generates future traffic maps for improved temporal consistency. A structure-consistent learning objective further encourages predictions to remain accurate, road-aligned, and spatially stable. Experiments across multiple cities show that RCSNet improves both forecasting accuracy and structural consistency. In same-city forecasting on Berlin, Antwerp, and Moscow, RCSNet reduces average MAE, MSE, and RMSE by 11.5%, 10.0%, and 5.1%, respectively, compared with the closest baseline. In cross-city testing on unseen Chicago and Bangkok, it reduces RMSE by 10.6% and 10.5% without target-city fine-tuning. Additional horizon-wise, road-structure, explainability, statistical, and efficiency analyses show that RCSNet produces more accurate, transferable, road-aligned, and computationally efficient traffic forecasts.