Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution
This work addresses a domain-specific problem in 3D point cloud understanding, offering an incremental improvement for researchers and practitioners in computer vision.
The paper tackles the challenge of modeling local surface geometry in 3D point clouds by proposing a Laplacian Unit (LU) that decouples convolution into local and global components to enhance local geometry learning. It shows that networks with LUs achieve competitive or superior performance on typical tasks, with connections to mean curvature flow for interpretation.
Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information. Most prior works model local geometry using various convolution operations. We observe that the convolution can be equivalently decomposed as a weighted combination of a local and a global component. With this observation, we explicitly decouple these two components so that the local one can be enhanced and facilitate the learning of local surface geometry. Specifically, we propose Laplacian Unit (LU), a simple yet effective architectural unit that can enhance the learning of local geometry. Extensive experiments demonstrate that networks equipped with LUs achieve competitive or superior performance on typical point cloud understanding tasks. Moreover, through establishing connections between the mean curvature flow, a further investigation of LU based on curvatures is made to interpret the adaptive smoothing and sharpening effect of LU. The code will be available.