WXinlong / ForeSeE

Task-Aware Monocular Depth Estimation for 3D Object Detection, AAAI2020

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Task-Aware Monocular Depth Estimation for 3D Object Detection

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

Installation

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

Dataset

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

Models

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

Testing

  cd experiments/foresee
  sh test.sh

Training

  cd experiments/foresee
  sh train.sh

Citations

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}
}
ezoic increase your site revenue

About

Task-Aware Monocular Depth Estimation for 3D Object Detection, AAAI2020


Languages

Language:Python 95.0%Language:C++ 2.5%Language:Cuda 2.0%Language:Shell 0.5%