Abstract
Geometrical structures and the internal local region relationship, such as symmetry, regular array, junction, etc., are essential for understanding a 3D shape. This paper proposes a point cloud feature extraction network named PointSCNet, to capture the geometrical structure information and local region correlation information of a point cloud. The PointSCNet consists of three main modules: the space-filling curve-guided sampling module, the information fusion module, and the channel-spatial attention module. The space-filling curve-guided sampling module uses Z-order curve coding to sample points that contain geometrical correlation. The information fusion module uses a correlation tensor and a set of skip connections to fuse the structure and correlation information. The channel-spatial attention module enhances the representation of key points and crucial feature channels to refine the network. The proposed PointSCNet is evaluated on shape classification and part segmentation tasks. The experimental results demonstrate that the PointSCNet outperforms or is on par with state-of-the-art methods by learning the structure and correlation of point clouds effectively.
Highlights
Point cloud is an ubiquitous form of 3D shapes and is suitable for countless applications in computer graphics due to its accessibility and expressiveness for 3D representation
Inspired by applications of attention mechanism for image processing, it can be inferred that, similar to image processing, information of critical local areas and feature channel of the point cloud has more impact on specific tasks. Based on these issues above, this paper proposes a point cloud feature extraction network, namely PointSCNet, which captures global structure and local region correlations of the point cloud for shape classification and part segmentation tasks
In the spatial attention module, the feature is fed to the Multi-Layer Perceptron (MLP) with shared weights, and the information on each channel is aggregated through the batch normalization layer and the pooling layer to obtain the spatial position attention weight
Summary
Point cloud is an ubiquitous form of 3D shapes and is suitable for countless applications in computer graphics due to its accessibility and expressiveness for 3D representation. There are inherent correlations between local regions of 3D objects, especially for Computer Aided Design (CAD) models or industrially manufactured products [20], such as the symmetric wing design of an airplane; the regular arrays of wheels for a car; or the distinct structure between the collar, sleeves and body part of a shirt These geometric correlations of local regions play a crucial role in 3D object understanding and are significant for typical point cloud processing tasks such as shape classification and part segmentation. Inspired by applications of attention mechanism for image processing, it can be inferred that, similar to image processing, information of critical local areas and feature channel of the point cloud has more impact on specific tasks Based on these issues above, this paper proposes a point cloud feature extraction network, namely PointSCNet, which captures global structure and local region correlations of the point cloud for shape classification and part segmentation tasks. The channel-spatial attention weights are learned for the refinement of the point cloud feature
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
