arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.00652cs.CV
收藏

PointSIFT:一种用于三维点云语义分割的SIFT类网络模型

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

Shanghai Jiao Tong University(上海交通大学);Tsinghua University(清华大学)

Mingyang Jiang, Yiran Wu, Tianqi Zhao, Zelin Zhao, Cewu Lu

摘要:

近年来,三维理解研究的热点是直接从点云数据中提取特征,这就需要对点云数据进行有效的形状模式描述。受优秀的二维形状描述子SIFT的启发,我们设计了一个名为PointSIFT的模块,该模块编码不同方向的信息,并自适应于形状的尺度。具体而言,设计了一个方向编码单元来描述8个关键方向,并通过堆叠多个方向编码单元来实现多尺度表示。PointSIFT模块可以集成到各种基于PointNet的体系结构中,以提高表示能力。大量的实验表明,我们的PointSIFT为基础的框架优于国家的最先进的方法在标准的基准数据集。代码和训练模型将与本文一起发布。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑