Journal
2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
Volume -, Issue -, Pages -Publisher
IEEE
Keywords
convolutional neural network; point cloud; shape analysis
Categories
Funding
- National Natural Science Foundation of China [61503243, U1405251]
- National Instrument Development Special Program of China [2013YQ03065101]
Ask authors/readers for more resources
As point cloud is a typical and significant type of geometric 3D data, deep learning on the classification and segmentation of point cloud has received widely interests recently. However, the critical problems to process the irregularity of point cloud and feature extraction of shape pattern have not yet been fully explored. In this paper, a geometric deep learning architecture based on our PointDoN module is presented. Inspired by the Difference of Normals (DoN) in traditional point clouds processing, our PointDoN module is a feature aggregation module combining DoN shape pattern descriptor with both 3D coordinates and extra features (such as RGB colors). Our PointDoN-based architecture can be flexibly applied to multiple point cloud processing tasks such as 3D shape classification and scene semantic segmentation. Experiments demonstrate that PointDoN model achieves state-of-the-art results on multiple types of challenging benchmark datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available