PyraPVConv: Efficient 3D Point Cloud Perception with Pyramid Voxel Convolution and Sharable Attention

Designing efficient deep learning models for 3D point cloud perception is becoming a major research direction. Point-voxel convolution (PVConv) Liu et al. (2019) is a pioneering research work in this topic. However, since with quite a few layers of simple 3D convolutions and linear point-voxel featu...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Yuhong, Peng, Weilong, Tang, Keke, Khan, Asad, Wei, Guodong, Fang, Meie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9122688/
https://www.ncbi.nlm.nih.gov/pubmed/35602612
http://dx.doi.org/10.1155/2022/2286818

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9122688/
https://www.ncbi.nlm.nih.gov/pubmed/35602612
http://dx.doi.org/10.1155/2022/2286818

Ejemplares similares