This project hosts the code for implementing the ForeSeE algorithm for depth estimation.

Task-Aware Monocular Depth Estimation for 3D Object Detection,
Xinlong Wang, Wei Yin, Tao Kong, Yuning Jiang, Lei Li, Chunhua Shen
AAAI, 2020

This implementation is based on VNL. Please refer to INSTALL.md for installation.

Please refer to KITTI dataset for details. The annotation files of KITTI Object subset used in our work are provided.

Download the trained model from this link and put it under experiments/foresee/.

  cd experiments/foresee
  sh test.sh

  cd experiments/foresee
  sh train.sh

Please consider citing our papers in your publications if the project helps your research. BibTeX reference is as follows.

@InProceedings{wang2020foresee, 
  title={Task-Aware Monocular Depth Estimation for 3D Object Detection}, 
  author = {Wang, Xinlong and Yin, Wei and Kong, Tao and Jiang, Yuning, and Li, Lei and Shen, Chunhua},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
  year={2020}
}