Recently, 3D understanding research sheds light on extracting features from point cloud directly, which requires effective shape pattern description of point clouds. Inspired by the outstanding 2D shape descriptor SIFT, 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-of-the-art method on standard benchmark datasets. The code and trained model will be published accompanied by this paper.
@article{arxiv.1807.00652,
title = {PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation},
author = {Mingyang Jiang and Yiran Wu and Tianqi Zhao and Zelin Zhao and Cewu Lu},
journal= {arXiv preprint arXiv:1807.00652},
year = {2018}
}