🛒MART🛒
MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction

Seongju Lee · Junseok Lee · Yeonguk Yu · Taeri Kim · Kyoobin Lee
ECCV 2024

ECCV Paper Poster Source Code Cite MART

---

This repo is the official implementation of "MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction (ECCV 2024)"

📢 Updates

• (2024.09.19) Official repository of 🛒MART🛒 is released
• (2024.09.30) Update ECCV poster

🪧 ECCV Poster

🚀 Getting Started

Environment Setup

1. Set up a python environment

conda create -n mart python=3.8
conda activate mart

2. Install requirements using the following command.

pip install -r requirements.txt

🚂 Train & Evaluation

• Trained and evaluated on NVIDIA GeForce RTX 3090 with python 3.8.

• The dataset is included in ./datasets/nba/

Train MART on the NBA dataset

python main_nba.py --config ./configs/mart_nba.yaml --gpu $GPU_IDs

Test MART on the NBA dataset after training

python main_nba.py --config ./configs/mart_nba.yaml --gpu $GPU_IDs --test

📊 Main Results

NBA dataset

• minADE_20: 0.727 [m]
• minFDE_20: 0.903 [m]

How to reproduce results

• The checkpoint is included in ./checkpoints/mart_nba_reproduce/

python main_nba.py --config ./configs/mart_nba_reproduce.yaml --gpu $GPU_IDs --test

📝 Citation

@article{lee2024mart,
  title={MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction},
  author={Lee, Seongju and Lee, Junseok and Yu, Yeonguk and Kim, Taeri and Lee, Kyoobin},
  journal={arXiv preprint arXiv:2407.21635},
  year={2024}
}

🤗 Acknowledgement

• The part of the code about the feature initialization is adapted from (GroupNet).
• Thanks for sharing the preprocessed NBA dataset and dataloader (LED).
• Thanks for providing the code of the Relational Transformer (RT). We implemented the RT from jax to pytorch.