期刊
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
卷 -, 期 -, 页码 10104-10112出版社
IEEE
DOI: 10.1109/CVPR.2019.01035
关键词
-
资金
- NVIDIA Corporation
In this paper, we propose a normal estimation method for unstructured 3D point clouds. This method, called Nesti-Net, builds on a new local point cloud representation which consists of multi-scale point statistics (MuPS), estimated on a local coarse Gaussian grid. This representation is a suitable input to a CNN architecture. The normals are estimated using a mixture of-experts (MoE) architecture, which relies on a data driven approach for selecting the optimal scale around each point and encourages sub -network specialization. Interesting insights into the network's resource distribution are provided. The scale prediction significantly improves robustness to different noise levels, point density variations and different levels of detail. We achieve state-of-the-art results on a benchmark synthetic dataset and present qualitative results on real scanned scenes.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据