CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
On learning the visibility for joint importance sampling of low-order scattering
Zhou, Guo1,2,3; Zhu, Dengming1,2; Li, Ting4; Wang, Zhaoqi1,2; Zhou, Yongquan5
2017-03-08
发表期刊NEUROCOMPUTING
ISSN0925-2312
卷号228页码:97-105
摘要Volumetric path tracing relies on importance sampling to stochastically construct light transport paths from an emitter to the sensor. Existing techniques incrementally sample path vertices or segments with respect to the local scattering property incorporating the geometry and scattering terms. Thus the joint probability density for drawing a path results in a product of the conditional densities each for a local sampling decision. We present a joint path sampling technique that additionally accounts for the spatially varying visibility due to transmittance and occlusion along a double scattering path. The directional density is formulated as a Gaussian mixture model being fitted to single scattered radiance by the online expectation maximization algorithm. It is first trained with samples oblivious to the visibility, then incrementally consumes an arbitrary number of samples being drawn from the actual scene. The resulting density in turn guides the directional sampling decision for both isotropic and anisotropic scattering. We demonstrate the benefit of our approach by integrating it into the unidirectional path tracing algorithm. The image noise is effectively reduced, even while rendering the heterogeneous participating media in the presence of complex opaque surfaces.
关键词Light transport simulation Participating media Online expectation-maximization Importance sampling
DOI10.1016/j.neucom.2016.09.086
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000393017900012
出版者ELSEVIER SCIENCE BV
引用统计
文献类型期刊论文
条目标识符http://119.78.100.204/handle/2XEOYT63/7589
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhou, Guo
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2.Beijing Key Lab Mobile Comp & Pervas Device, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.CNCERT CC, Beijing 100029, Peoples R China
5.Guangxi Univ Nationalities, Coll Informat Sci & Engn, Nanning 530006, Peoples R China
推荐引用方式
GB/T 7714
Zhou, Guo,Zhu, Dengming,Li, Ting,et al. On learning the visibility for joint importance sampling of low-order scattering[J]. NEUROCOMPUTING,2017,228:97-105.
APA Zhou, Guo,Zhu, Dengming,Li, Ting,Wang, Zhaoqi,&Zhou, Yongquan.(2017).On learning the visibility for joint importance sampling of low-order scattering.NEUROCOMPUTING,228,97-105.
MLA Zhou, Guo,et al."On learning the visibility for joint importance sampling of low-order scattering".NEUROCOMPUTING 228(2017):97-105.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhou, Guo]的文章
[Zhu, Dengming]的文章
[Li, Ting]的文章
百度学术
百度学术中相似的文章
[Zhou, Guo]的文章
[Zhu, Dengming]的文章
[Li, Ting]的文章
必应学术
必应学术中相似的文章
[Zhou, Guo]的文章
[Zhu, Dengming]的文章
[Li, Ting]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。