Associatively Segmenting Instances and Semantics in Point Clouds, CVPR 2019
MIT License
The full paper is available at: https://arxiv.org/abs/1902.09852. Qualitative results of ASIS on the S3DIS and vKITTI test fold:
The code has been tested with Python 2.7 on Ubuntu 14.04.
python collect_indoor3d_data.py
python gen_h5.py
cd data && python generate_input_list.py
cd ..
Compile TF Operators
Refer to PointNet++
Training
cd models/ASIS/
ln -s ../../data .
sh +x train.sh 5
python eval_iou_accuracy.py
Note: We test on Area5 and train on the rest folds in default. 6 fold CV can be conducted in a similar way.
If our work is useful for your research, please consider citing:
@inproceedings{wang2019asis,
title={Associatively Segmenting Instances and Semantics in Point Clouds},
author={Wang, Xinlong and Liu, Shu and Shen, Xiaoyong and Shen, Chunhua, and Jia, Jiaya},
booktitle={CVPR},
year={2019}
}
This code largely benefits from following repositories: PointNet++, SGPN, DGCNN and DiscLoss-tf