/3DCFS

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

Primary LanguagePython

3DCFS

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

Framework

illustration

The illustration of CFSM seen as follow

3DCFS architecture

The details of our proposed 3DCFS architecture seen as follow

Visulization

Qualitative results on the S3DIS

Qualitative results on the ShapeNet

Evaluation

Quantitative results on the S3DIS

The results of our method on S3DIS Area5 and 6-Fold CV respectively.

Usage

1.clone the 3DCFS repository:

cd ~
git clone https://github.com/Biotan/3DCFS

2.download the dataset such as S3DIS and modify the path in train and test file.

3.prepare the environment including tensorflow1.2.0 and python2.7.

  1. make the code of pointnet according to [Pointnet].

  2. trainning

cd 3DCFS/models
python train.py
  1. testing and evaluation
python test.py && python eval_iou_accuracy.py