UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction

Lan Feng^1*, Mohammadhossein Bahari^1*, Kaouther Messaoud Ben Amor¹, Éloi Zablocki²,
Matthieu Cord^2,3, Alexandre Alahi¹

¹EPFL, ²Valeo.ai, ³Sorbonne University
^*Equal contribution

Accepted to ECCV 2024

Code | Paper

Overview

Fig. 1 Overview of UniTraj

UniTraj, a comprehensive open-source framework for vehicle trajectory prediction, integrating various datasets, models, and evaluations. It offers a unified platform for comprehensive research in this field.

Video Introduction

Reference

@article{feng2024unitraj,
  title={UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction},
  author={Feng, Lan and Bahari, Mohammadhossein and Amor, Kaouther Messaoud Ben and Zablocki, {\'E}loi and Cord, Matthieu and Alahi, Alexandre},
  journal={arXiv preprint arXiv:2403.15098},
  year={2024}
}