- This is the official implementation of the paper: DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets (ICCV 2021).
- DenseTNT v1.0 was released in November 1st, 2021.
Requires:
- Python 3.6+
- pytorch 1.6+
pip install -r requirements.txt
https://github.com/argoai/argoverse-api
Compile a .pyx file into a C file using Cython:
cd src/
cython -a utils_cython.pyx && python setup.py build_ext --inplace
Results on Argoverse motion forecasting validation set:
minADE | minFDE | Miss Rate | |
---|---|---|---|
DenseTNT w/ 100ms optimization | 0.80 | 1.27 | 7.0% |
DenseTNT w/ 100ms optimization (minFDE) | 0.73 | 1.05 | 9.8% |
DenseTNT w/ goal set predictor (online) | 0.82 | 1.37 | 7.0% |
# for carla
bash train_carla.sh
# for argoverse
bash train.sh
bash val.sh
# for optimize mFDE
bash val_MRmFDE.sh
bash comparision.sh
bash inference.sh
If you find our work useful for your research, please consider citing the paper:
@inproceedings{densetnt,
title={Densetnt: End-to-end trajectory prediction from dense goal sets},
author={Gu, Junru and Sun, Chen and Zhao, Hang},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
pages={15303--15312},
year={2021}
}