With the development of 3D scanning technology, a huge volume of point cloud data has been collected at a lower cost. The huge data set is the main burden during the data processing of point clouds, so point cloud simplification is critical. The main aim of point cloud simplification is to reduce data volume while preserving the data features. Therefore, this paper provides a new method for point cloud simplification, named FPPS (feature-preserved point cloud simplification). In FPPS, point cloud simplification entropy is defined, which quantifies features hidden in point clouds. According to simplification entropy, the key points including the majority of the geometric features are selected. Then, based on the natural quadric shape, we introduce a point cloud matching model (PCMM), by which the simplification rules are set. Additionally, the similarity between PCMM and the neighbors of the key points is measured by the shape operator. This represents the criteria for the adaptive simplification parameters in FPPS. Finally, the experiment verifies the feasibility of FPPS and compares FPPS with other four-point cloud simplification algorithms. The results show that FPPS is superior to other simplification algorithms. In addition, FPPS can partially recognize noise.

The semantic segmentation of point clouds has significant applications in fields such as autonomous driving, robot vision, and smart cities. As LiDAR technology continues to develop, point clouds have gradually become the main type of 3D data. However, due to the disordered and scattered nature of point cloud data, it is challenging to effectively segment them semantically. A three-dimensional (3D) shape provides an important means of studying the spatial relationships between different objects and their structures in point clouds. Thus, this paper proposes a semi-supervised semantic segmentation network for point clouds based on 3D shape, which we call SBSNet. This network groups and encodes the geometric information of 3D objects to form shape features. It utilizes an attention mechanism and local information fusion to capture shape context information and calculate the data features. The experimental results showed that the proposed method achieved an overall intersection ratio of 85.3% in the ShapeNet dataset and 90.6% accuracy in the ModelNet40 dataset. Empirically, it showed strong performance on par or even better than state-of-the-art models.