No abstract

Recently, 3D understanding research sheds light on extracting features from point cloud directly [22,24], which requires effective shape pattern description of point clouds. Inspired by the outstanding 2D shape descriptor SIFT [15], we design a module called PointSIFT that encodes information of different orientations and is adaptive to scale of shape. Specifically, an orientation-encoding unit is designed to describe eight crucial orientations, and multi-scale representation is achieved by stacking several orientation-encoding units. PointSIFT module can be integrated into various PointNet-based architecture to improve the representation ability. Extensive experiments show our PointSIFT-based framework outperforms state-ofthe-art method on standard benchmark datasets. The code and trained model will be published accompanied by this paper.

No abstract

No abstract