点云
切线
计算机科学
分割
人工智能
点(几何)
曲面(拓扑)
切线空间
深度学习
比例(比率)
算法
计算机视觉
数学
几何学
地图学
地理
作者
Maxim Tatarchenko,Jaesik Park,Vladlen Koltun,Qian-Yi Zhou
标识
DOI:10.1109/cvpr.2018.00409
摘要
We present an approach to semantic scene analysis using deep convolutional networks. Our approach is based on tangent convolutions - a new construction for convolutional networks on 3D data. In contrast to volumetric approaches, our method operates directly on surface geometry. Crucially, the construction is applicable to unstructured point clouds and other noisy real-world data. We show that tangent convolutions can be evaluated efficiently on large-scale point clouds with millions of points. Using tangent convolutions, we design a deep fully-convolutional network for semantic segmentation of 3D point clouds, and apply it to challenging real-world datasets of indoor and outdoor 3D environments. Experimental results show that the presented approach outperforms other recent deep network constructions in detailed analysis of large 3D scenes.
科研通智能强力驱动
Strongly Powered by AbleSci AI