PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling

TL;DR

The paper tackles the challenge of learning geometry and local-region correlations from unstructured point clouds to improve shape classification and part segmentation. It proposes PointSCNet, which integrates space-filling curve guided sampling via Z-order encoding, a correlation-based information fusion module to jointly model structure and local-region interactions, and a channel-spatial attention mechanism to refine salient features. Experiments on ModelNet40 and ShapeNet demonstrate competitive accuracy and effective feature refinement, with ablations confirming the contributions of each module. The results indicate that explicitly modeling structure and inter-region correlations enhances 3D understanding and can be extended to other vision tasks.

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.

Figures (10)

• Figure S1: Learning structure and correlation on point cloud based on space filling curve guided sampling. Columns shown from left to right are the original input point cloud, points sampled by the Z-order space filling curve, and the point cloud heat map based on response of points to the proposed network, respectively.
• Figure S2: Model architecture of PointSCNet: The original point cloud is fed to a sampling&grouping block. Then a Z-order sampling block is designed for further generation of local regions. After the sampled point cloud feature is extracted, the feature fusion module is designed to learn the structure and correlation information. At last the point cloud feature is forwarded to the PointCSA block which is based on channel-spatial attention mechanism to get the refined feature for classification and segmentation.
• Figure S3: The point cloud structure obtained by sampling 1024 points in the original point cloud using the Z-order space filling curve.
• Figure S4: Sampling strategy based on Z-order curve sorting. Equally spaced points are sampled, the spacing is set to 3 in the figure.
• Figure S5: The correlation tensor is designed for the evaluation of the correlation between the local feature and structure feature. $N^{'}$ and $N^{"}$ represent the number of points sampled via FPS and Z-order sampling block, $C$ is the feature channel of points.