RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

RfD-Net

Yinyu Nie, Ji Hou, Xiaoguang Han, Matthias Nießner
In CVPR, 2021.

From an incomplete point cloud of a 3D scene (left), our method learns to jointly understand the 3D objects and reconstruct instance meshes as the output (right).

Install

This implementation uses Python 3.6, Pytorch1.7.1, cudatoolkit 11.0. We recommend to use conda to deploy the environment.
```
conda env create -f environment.yml
conda activate rfdnet
```
```
pip install -r requirements.txt
```
Next, compile the external libraries by
```
python setup.py build_ext --inplace
```

Install PointNet++ by

cd external/pointnet2_ops_lib
pip install .

Demo

The pretrained model can be downloaded here. Put the pretrained model in the directory as below

out/pretrained_models/pretrained_weight.pth

A demo is illustrated

To finish reading, please visit source site