PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation

Recently, 3D understanding research pays more attention to extracting the feature from point cloud directly. Therefore, exploring shape pattern description in points is essential. Inspired by SIFT that is an outstanding 2D shape representation, we design a PointSIFT module that encodes information of different orientations and is adaptive to scale of shape. Especially, an orientation-encoding unit is designed to describe eight crucial orientations. Thus, by stacking several orientation-encoding units, we can get the multi-scale representation. Extensive experiments show our PointS IF T-based framework outperforms state-of-the-art method on standard benchmarking datasets. The code and trained model will be published accompanied by this paper.