【文件属性】:
文件名称:3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
文件大小:616KB
文件格式:PDF
更新时间:2021-07-24 07:53:29
稀疏神经网络 3D语义分割 子流形 CVPR-18
Convolutional networks are the de-facto standard for analyzing
spatio-temporal data such as images, videos, and
3D shapes. Whilst some of this data is naturally dense (e.g.,
photos), many other data sources are inherently sparse. Examples
include 3D point clouds that were obtained using
a LiDAR scanner or RGB-D camera. Standard “dense”
implementations of convolutional networks are very inefficient
when applied on such sparse data. We introduce new
sparse convolutional operations that are designed to process
spatially-sparse data more efficiently, and use them
to develop spatially-sparse convolutional networks. We
demonstrate the strong performance of the resulting models,
called submanifold sparse convolutional networks (SSCNs),
on two tasks involving semantic segmentation of 3D
point clouds. In particular, our models outperform all prior
state-of-the-art on the test set of a recent semantic segmentation
competition
网友评论
相关文章
- Fully convolutional networks for semantic segmentation
- encoding sentences with graph convolutional networks for semantic role labeling
- Semantic Segmentation using Adversarial Networks.pdf
- Semantic Breast Tumor Segmentation by CNN: Semantic Breast Tumor Segmentation by Convolutional Neural Network in MRI 图像-matlab开发