created by Can Chen, Luca Zanotti Fragonara, Antonios Tsourdos from Cranfield University

[Paper]

We propose a graph attention based point neural network, named GAPNet, to learn shape representations for point cloud. Experiments show state-of-the-art performance in shape classification and semantic part segmentation tasks.

In this repository, we release code for training a GAPNet classification network on ModelNet40 dataset and a part segmentation network on ShapeNet part dataset.

• TensorFlow

• Run the training script:

python train.py

• Run the evaluation script after training finished:

python evaluate.py --model=network --model_path=log/epoch_185_model.ckpt

• Run the training script:

python train_multi_gpu.py

• Run the evaluation script after training finished:

python test.py --model_path train_results/trained_models/epoch_130.ckpt

Please cite this paper if you want to use it in your work.

@article{chen2019gapnet,
  title={GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud},
  author={Chen, Can and Fragonara, Luca Zanotti and Tsourdos, Antonios},
  journal={arXiv preprint arXiv:1905.08705},
  year={2019}
}

MIT License