Enhancing Local Feature Learning Using Diffusion for 3D Point Cloud Understanding
This work addresses a specific problem in 3D point cloud understanding for researchers and practitioners, but it is incremental as it builds on existing edge-aware methods.
The paper tackles the challenge of unclear edge contributions in 3D point cloud learning by proposing a method that automatically learns to enhance or suppress edges while maintaining transparency, achieving competitive performance in classification and segmentation tasks.
Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this study, we propose a method that automatically learns to enhance/suppress edges while keeping the its working mechanism clear. First, we theoretically figure out how edge enhancement/suppression works. Second, we experimentally verify the edge enhancement/suppression behavior. Third, we empirically show that this behavior improves performance. In general, we observe that the proposed method achieves competitive performance in point cloud classification and segmentation tasks.