Cross-Shape Attention for Part Segmentation of 3D Point Clouds
This addresses part segmentation accuracy for 3D point clouds, which is an incremental improvement over existing methods.
The paper tackles 3D shape segmentation by proposing a cross-shape attention mechanism that propagates point-wise features across shapes, achieving state-of-the-art results on the PartNet dataset.
We present a deep learning method that propagates point-wise feature representations across shapes within a collection for the purpose of 3D shape segmentation. We propose a cross-shape attention mechanism to enable interactions between a shape's point-wise features and those of other shapes. The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point-wise feature representations for shape segmentation. Our method also proposes a shape retrieval measure to select suitable shapes for cross-shape attention operations for each test shape. Our experiments demonstrate that our approach yields state-of-the-art results in the popular PartNet dataset.