Skip to content

Latest commit

 

History

History
105 lines (78 loc) · 3.25 KB

README.md

File metadata and controls

105 lines (78 loc) · 3.25 KB

JSPNet: Learning Joint Semantic & Instance Segmentation of Point Clouds via Feature Self-similarity and Cross-task Probability

Overview

Dependencies

The code has been tested with Python 3.5 on Ubuntu 16.04.

Data and Model

  • Download 3D indoor parsing dataset (S3DIS Dataset). Version 1.2 of the dataset is used in this work.
python utils/s3dis_utils/collect_indoor3d_data.py
python utils/s3dis_utils/s3dis_gen_h5.py
cd data && python generate_input_list.py && python generate_train_test_list.py
cd ..
  • (optional) Prepared HDF5 data for training is available here.

Results

baseline S&I module mIoU mPre para
JSPNet w/o 52.3 52.0
JSPNet SIFF 54.7 57.9
JSPNet PIFF 55.2 60.2 model
JSPNet SIFF&PIFF 55.8 59.3 model

Usage

  • Compile TF Operators

    Refer to PointNet++

  • Training, Test, and Evaluation

cd models/JSPNet/
ln -s ../../data .

# training
python train.py \
--gpu 0 \
--data_root ./ \
--data_type numpy \
--max_epoch  100  \
--log_dir ../../logs/train_5 \
--input_list data/train_file_list_woArea5.txt

# estimate_mean_ins_size 
python estimate_mean_ins_size.py \
--data_root ./ \
--input_list data/train_hdf5_file_list_woArea5.txt \
--out_dir ../../logs/train_5

# test
python test.py \
--gpu 0 \
--data_root ./ \
--data_type hdf5 \
--bandwidth 0.6   \
--num_point 4096  \
--log_dir ../../logs/test_5 \
--model_path ../../logs/train_5/epoch_99.ckpt \
--input_list  data/test_hdf5_file_list_Area5.txt

# evaluation
python eval_iou_accuracy.py --log_dir ../../logs/test_5

Note: We test on Area5 and train on the rest folds in default. 6 fold CV can be conducted in a similar way.

Citation

If our work is useful for your research, please consider citing:

  @article{chen2021jspnet,
    title={JSPNet: Learning Joint Semantic \& Instance Segmentation of Point Clouds via Feature Self-similarity and Cross-task Probability},
    author={Chen, Feng and Wu, Fei and Gao, Guangwei and Ji, Yimu and Xu, Jing and Jiang, Guo-Ping and Jing, Xiao-Yuan},
    journal={Pattern Recognition},
    pages={108250},
    year={2021},
    publisher={Elsevier}
  }

Acknowledgements

This code largely benefits from following repositories: ASIS, PointNet++, PointConv, SGPN DiscLoss-tf JSNet Pytorch-Encoding