Abstract
Recently, a lot of attention is given to deep learning on raw 3D point clouds. Existing approaches, however, either exploit the global shape feature without paying attention to the local features or hierarchically exploit local features with little attention to the global shape feature. In this paper, we proposed Fused Feature Point Network (FFPointNet), a deep neural network for learning on raw point clouds that exploits both local and global shape features. Specifically, we designed a novel module, ChannelNet, a simple and effective module that exploits global shape features using 1D convolutions. ChannelNet uses only 0.041 million parameters, making it easy to plug in the generic PointNet++ backbone to exploits both local and global shape structures for better contextual representation. Experiments carried out showed that by fusing PointNet++ feature with ChannelNet feature, we gained an improved classification accuracy over PointNet++ by 2.2% on the popular ModelNet40 dataset; and an improved class mean intersection over union of 1.4% on the popular ShapeNetParts dataset.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.