Geometric Attention for Prediction of Differential Properties in 3D Point Clouds
This work addresses a key challenge in geometry processing for applications like 3D modeling and computer graphics, though it appears incremental as it builds on existing learnable approaches.
The paper tackled the problem of estimating differential geometric properties like normals and sharp feature lines from raw 3D point clouds, which is crucial for improving meshing and surface reconstruction, and presented a geometric attention mechanism that demonstrated usefulness in experiments for predicting these properties.
Estimation of differential geometric quantities in discrete 3D data representations is one of the crucial steps in the geometry processing pipeline. Specifically, estimating normals and sharp feature lines from raw point cloud helps improve meshing quality and allows us to use more precise surface reconstruction techniques. When designing a learnable approach to such problems, the main difficulty is selecting neighborhoods in a point cloud and incorporating geometric relations between the points. In this study, we present a geometric attention mechanism that can provide such properties in a learnable fashion. We establish the usefulness of the proposed technique with several experiments on the prediction of normal vectors and the extraction of feature lines.