| Summary: | This study introduces a novel approach, Local Spatial Projection Convolution (LSPConv), for point cloud classification and semantic segmentation. Unlike conventional methods utilizing relative coordinates for local geometric information, our motivation stems from the inadequacy of existing techniques for representing the intricate spatial organization of unconsolidated and irregular 3D point clouds. To address this limitation, we propose a Local Spatial Projection Module utilizing a vector projection strategy, designed to capture comprehensive local spatial information more effectively. Moreover, recent studies emphasize the importance of anisotropic kernels for point cloud feature extraction, considering the distinct contributions of individual neighboring points. To cater to this requirement, we introduce the Feature Weight Assignment (FWA) Module to assign weights to neighboring points, enhancing the anisotropy crucial for accurate feature extraction. Additionally, we introduce an Anisotropic Relative Feature Encoding Module that adaptively encodes points based on their relative features, further amplifying the anisotropic characteristics. Our approaches achieve remarkable results for point cloud classification and segmentation in several benchmark datasets based on extensive qualitative and quantitative evaluation.
|
|---|