The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing.This paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud learning....The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing.This paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud learning.PCT is based on Transformer,which achieves huge success in natural language processing and displays great potential in image processing.It is inherently permutation invariant for processing a sequence of points,making it well-suited for point cloud learning.To better capture local context within the point cloud,we enhance input embedding with the support of farthest point sampling and nearest neighbor search.Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification,part segmentation,semantic segmentation,and normal estimation tasks.展开更多
The unique characteristics of ultrafast lasers,such as picosecond and femtosecond lasers,have opened up new avenues in materials processing that employ ultrashort pulse widths and extremely high peak intensities.Thus,...The unique characteristics of ultrafast lasers,such as picosecond and femtosecond lasers,have opened up new avenues in materials processing that employ ultrashort pulse widths and extremely high peak intensities.Thus,ultrafast lasers are currently used widely for both fundamental research and practical applications.This review describes the characteristics of ultrafast laser processing and the recent advancements and applications of both surface and volume processing.Surface processing includes micromachining,microand nanostructuring,and nanoablation,while volume processing includes two-photon polymerization and three-dimensional(3D)processing within transparent materials.Commercial and industrial applications of ultrafast laser processing are also introduced,and a summary of the technology with future outlooks are also given.展开更多
分析了空间数据的维数及其表示,讨论了三维地理信息系统中两类不同的空间数据结构,即基于表面表示的数据结构和基于体表示的数据结构。分析了边界表示(BR)、结构实体几何法(CSG)、非均匀有理 B 样条(NURBS)、八叉树(Octree)和不规则四面...分析了空间数据的维数及其表示,讨论了三维地理信息系统中两类不同的空间数据结构,即基于表面表示的数据结构和基于体表示的数据结构。分析了边界表示(BR)、结构实体几何法(CSG)、非均匀有理 B 样条(NURBS)、八叉树(Octree)和不规则四面体(TEN)等空间数据结构的特点和应用。展开更多
基金supported by the National Natural Science Foundation of China(Project Number 61521002)the Joint NSFC–DFG Research Program(Project Number 61761136018).
文摘The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing.This paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud learning.PCT is based on Transformer,which achieves huge success in natural language processing and displays great potential in image processing.It is inherently permutation invariant for processing a sequence of points,making it well-suited for point cloud learning.To better capture local context within the point cloud,we enhance input embedding with the support of farthest point sampling and nearest neighbor search.Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification,part segmentation,semantic segmentation,and normal estimation tasks.
文摘The unique characteristics of ultrafast lasers,such as picosecond and femtosecond lasers,have opened up new avenues in materials processing that employ ultrashort pulse widths and extremely high peak intensities.Thus,ultrafast lasers are currently used widely for both fundamental research and practical applications.This review describes the characteristics of ultrafast laser processing and the recent advancements and applications of both surface and volume processing.Surface processing includes micromachining,microand nanostructuring,and nanoablation,while volume processing includes two-photon polymerization and three-dimensional(3D)processing within transparent materials.Commercial and industrial applications of ultrafast laser processing are also introduced,and a summary of the technology with future outlooks are also given.
