SRG-Net: Unsupervised Segmentation for Terracotta Warrior Point Cloud with 3D Pointwise CNN methods

In this paper, we present a seed-region-growing CNN(SRG-Net) for unsupervised part segmentation with 3D point clouds of terracotta warriors. Previous neural network researches in 3D are mainly about supervised classification, clustering, unsupervised representation and reconstruction. There are few researches focusing on unsupervised point cloud part segmentation. To address these problems, we present a seed-region-growing CNN(SRG-Net) for unsupervised part segmentation with 3D point clouds of terracotta warriors. Firstly, we propose our customized seed region growing algorithm to coarsely segment the point cloud. Then we present our supervised segmentation and unsupervised reconstruction networks to better understand the characteristics of 3D point clouds. Finally, we combine the SRG algorithm with our improved CNN using a refinement method called SRG-Net to conduct the segmentation tasks on the terracotta warriors. Our proposed SRG-Net are evaluated on the terracotta warriors data and the benchmark dataset of ShapeNet with measuring mean intersection over union(mIoU) and latency. The experimental results show that our SRG-Net outperforms the state-of-the-art methods. Our code is available at https://github.com/hyoau/SRG-Net.