Multi-Head Attentional Point Cloud Classification and Segmentation Using Strictly Rotation-Invariant Representations

Multi-Head Attentional Point Cloud Classification and Segmentation Using Strictly Rotation-Invariant Representations

Point cloud processing plays an increasingly essential role in three-dimensional (3D) computer vision target, scene parsing, environmental perception, etc. Compared with using aligned point cloud data for classification and segmentation, the strictly rotation-invariant representations show enough ro...

Full description

Bibliographic Details
Main Authors: Zhiyong Tao, Yixin Zhu, Tong Wei, Sen Lin
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Point cloud
deep learning
strictly rotation-invariant representations
attention coding
classification and segmentation
Online Access:https://ieeexplore.ieee.org/document/9427563/

Internet

https://ieeexplore.ieee.org/document/9427563/

Similar Items