Our pipeline first collects a sequence of monocular RGB images and predicted depth for large-scale dense 3D scene reconstruction, and then automatically place virtual objects on top of ground in order to generate realistic traffic scene data (manual mode is enabled as well for fine tunning or generating 3D occlusion awareness).
1. Depth Prediction
2. Reconstruction
3. Augmentation
Auto Mode:
Manual Mode:
Create our environment with
conda create -n rec4aug python=3.6.6
After activate the environment rec4aug
, you need to install:
conda install pytorch=0.4.1 torchvision=0.2.1 -c pytorch
pip install open3d
pip install opencv-python
We use imagemagick to transform the output of monodepth to the format taken by InfiniTAM
You can simply use terminal under this directory and type
bash run_pipeline.sh
to run the whole pipeline of our project. You can choose whether to skip a stage( e.g. reconstruction using open3d) by entering y or N with respect to corresponding shell prompt.