Academic Journal
面向高分辨率激光扫描点云的三维建筑物风格化渲染方法.
| العنوان: | 面向高分辨率激光扫描点云的三维建筑物风格化渲染方法. (Chinese) |
|---|---|
| Alternate Title: | A method on stylized rendering of 3-D building via high-resolution laser scanning point clouds. (English) |
| المؤلفون: | 唐翔, 王伟鹏, 罗欢, 郭迎亚 |
| المصدر: | Journal of Fuzhou University; Dec2021, Vol. 49 Issue 6, p761-766, 6p |
| Abstract (English): | Aiming at solving the non, photorealistic rendering problem of high, resolution laser scanning point clouds, a stylized rendering method is proposed to render the point clouds to improve the visual effect of high, resolution 3D building point clouds. Firstly, to handle computational burden brought by the large amount points in the high, resolution point clouds, a farthest point sampling method is proposed to reduce the number of points while preserving its 3D structural features. Then, to conduct the cross, dimensional style transfer, a neural network, based style rendering method is introduced to achieve the visual style transferred from 2D images to 3D mesh. Finally, in order to transfer visualiza, tion information from 3D mesh to 3D point clouds quickly and efficiently, we proposed a K, D tree based fusion method to establish the mapping relationship between 3D mesh and 3D point cloud. Experiments demonstrate that the proposed framework can effectively transform the style of a given 2D image into a 3D building style, which promotes the visual effects of the high, resolution laser scanning point clouds of buildings. [ABSTRACT FROM AUTHOR] |
| Abstract (Chinese): | 针对点云的非真实感渲染问题, 提出一种面向高分辨率点云数据的风格化渲染方法, 以提高点云数据展 示的艺术性. 首先, 针对高分辨率点云中海量三维点所带来的计算量问题, 提出远距离点采样方法, 在实现精 简数据的同时保留其三维结构特征, 然后, 针对跨维度的风格迁移问题, 引入基于深度神经网络的风格化渲染 方法, 实现二维图像至三维网格的风格迁移, 最后, 为了快速且高效地将可视化风格信息从三维网格向三维点 云进行传递, 提出基于 K￣D 树的网格数据与点云数据的融合方法, 以建立两种数据之间的映射关系. 实验结果 表明, 所提出的方法可有效地将给定二维图像的风格转化为目标三维建筑物的风格, 增强了高分辨率三维建 筑物点云数据的展示效果. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Fuzhou University is the property of Journal of Fuzhou University, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| قاعدة البيانات: | Complementary Index |
| ResultId |
1 |
|---|---|
| Header |
edb Complementary Index 154510773 937 6 Academic Journal academicJournal 937.311218261719 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edb&AN=154510773&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
|
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => 面向高分辨率激光扫描点云的三维建筑物风格化渲染方法. (Chinese)
)
Array ( [Name] => TitleAlt [Label] => Alternate Title [Group] => TiAlt [Data] => A method on stylized rendering of 3-D building via high-resolution laser scanning point clouds. (English) ) Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22唐翔%22">唐翔</searchLink><br /><searchLink fieldCode="AR" term="%22王伟鹏%22">王伟鹏</searchLink><br /><searchLink fieldCode="AR" term="%22罗欢%22">罗欢</searchLink><br /><searchLink fieldCode="AR" term="%22郭迎亚%22">郭迎亚</searchLink> ) Array ( [Name] => TitleSource [Label] => Source [Group] => Src [Data] => Journal of Fuzhou University; Dec2021, Vol. 49 Issue 6, p761-766, 6p ) Array ( [Name] => AbstractNonEng [Label] => Abstract (English) [Group] => Ab [Data] => Aiming at solving the non, photorealistic rendering problem of high, resolution laser scanning point clouds, a stylized rendering method is proposed to render the point clouds to improve the visual effect of high, resolution 3D building point clouds. Firstly, to handle computational burden brought by the large amount points in the high, resolution point clouds, a farthest point sampling method is proposed to reduce the number of points while preserving its 3D structural features. Then, to conduct the cross, dimensional style transfer, a neural network, based style rendering method is introduced to achieve the visual style transferred from 2D images to 3D mesh. Finally, in order to transfer visualiza, tion information from 3D mesh to 3D point clouds quickly and efficiently, we proposed a K, D tree based fusion method to establish the mapping relationship between 3D mesh and 3D point cloud. Experiments demonstrate that the proposed framework can effectively transform the style of a given 2D image into a 3D building style, which promotes the visual effects of the high, resolution laser scanning point clouds of buildings. [ABSTRACT FROM AUTHOR] ) Array ( [Name] => AbstractNonEng [Label] => Abstract (Chinese) [Group] => Ab [Data] => 针对点云的非真实感渲染问题, 提出一种面向高分辨率点云数据的风格化渲染方法, 以提高点云数据展 示的艺术性. 首先, 针对高分辨率点云中海量三维点所带来的计算量问题, 提出远距离点采样方法, 在实现精 简数据的同时保留其三维结构特征, 然后, 针对跨维度的风格迁移问题, 引入基于深度神经网络的风格化渲染 方法, 实现二维图像至三维网格的风格迁移, 最后, 为了快速且高效地将可视化风格信息从三维网格向三维点 云进行传递, 提出基于 K￣D 树的网格数据与点云数据的融合方法, 以建立两种数据之间的映射关系. 实验结果 表明, 所提出的方法可有效地将给定二维图像的风格转化为目标三维建筑物的风格, 增强了高分辨率三维建 筑物点云数据的展示效果. [ABSTRACT FROM AUTHOR] ) Array ( [Name] => Abstract [Label] => [Group] => Ab [Data] => <i>Copyright of Journal of Fuzhou University is the property of Journal of Fuzhou University, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Identifiers] => Array
(
[0] => Array
(
[Type] => doi
[Value] => 10.7631/issn.1000-2243.20495
)
)
[Languages] => Array
(
[0] => Array
(
[Code] => chi
[Text] => Chinese
)
)
[PhysicalDescription] => Array
(
[Pagination] => Array
(
[PageCount] => 6
[StartPage] => 761
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => 面向高分辨率激光扫描点云的三维建筑物风格化渲染方法.
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => 唐翔
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => 王伟鹏
)
)
)
[2] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => 罗欢
)
)
)
[3] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => 郭迎亚
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 01
[M] => 12
[Text] => Dec2021
[Type] => published
[Y] => 2021
)
)
[Identifiers] => Array
(
[0] => Array
(
[Type] => issn-print
[Value] => 10002243
)
)
[Numbering] => Array
(
[0] => Array
(
[Type] => volume
[Value] => 49
)
[1] => Array
(
[Type] => issue
[Value] => 6
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Journal of Fuzhou University
[Type] => main
)
)
)
)
)
)
)
|
| IllustrationInfo |