PCT:Point cloud transformer

作     者：Meng-Hao Guo Jun-Xiong Cai Zheng-Ning Liu Tai-Jiang Mu Ralph R.Martin Shi-Min Hu Meng-Hao Guo;Jun-Xiong Cai;Zheng-Ning Liu;Tai-Jiang Mu;Ralph R.Martin;Shi-Min Hu

作者机构：BNRistDepartment of Computer Science and TechnologyTsinghua UniversityBeiing 100084China Cardiff UniversityCardiff CF243 

出 版 物：《Computational Visual Media》 (计算可视媒体（英文版）)

年 卷 期：2021年第7卷第2期

页      面：187-199页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(Project Number 61521002) the Joint NSFC–DFG Research Program(Project Number 61761136018) 

主　　题：3D computer vision deep learning point cloud processing Transformer 

摘      要：The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud *** paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud *** is based on Transformer,which achieves huge success in natural language processing and displays great potential in image *** is inherently permutation invariant for processing a sequence of points,making it well-suited for point cloud *** better capture local context within the point cloud,we enhance input embedding with the support of farthest point sampling and nearest neighbor *** experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification,part segmentation,semantic segmentation,and normal estimation tasks.