基于感知的室内场景的多视点渲染优化

doi:10.3969/j.issn.0253-2778.2018.02.008

中国科学技术大学学报 ›› 2018, Vol. 48 ›› Issue (2): 140-147.DOI: 10.3969/j.issn.0253-2778.2018.02.008

基于感知的室内场景的多视点渲染优化

汲梦宇，刘利刚

中国科学技术大学数学科学学院，安徽合肥 230026

收稿日期:2016-12-08 修回日期:2017-04-06 出版日期:2018-02-28 发布日期:2018-02-28
通讯作者: 刘利刚
作者简介:汲梦宇，女，1994年生，硕士. 研究方向：计算机图形学. E-mail: jimengyu@mail.ustc.edu.cn
基金资助:
国家自然科学基金(61672482, 11626253), 中国科学院“百人计划”资助.

Perception-aware multi-view rendering optimization for indoor scenes

JI Mengyu,LIU Ligang

School of Mathematical Sciences，University of Science and Technology of China，Hefei 230026, China）

Received:2016-12-08 Revised:2017-04-06 Online:2018-02-28 Published:2018-02-28

摘要/Abstract

摘要： 研究了室内场景的自适应多视点渲染优化问题. 对于输入的三维室内场景模型，首先定义了一个新颖的基于几何信息、结构信息及美学信息的视点感知度量函数; 进而建立了一个多视点整体优化模型; 然后利用模拟退火算法优化得到用户指定个数的多视点集合，最后渲染出图. 实验结果表明，对于室内场景多视点渲染优化这一问题，提出的方法能够自适应地得到一系列全面且美观的渲染图片.

关键词: 室内场景, 多视点渲染, 模拟退火

Abstract: Multi-view rendering optimization for indoor scenes in the process of interior design was studied. Given an indoor scene model，firstly，a novel and perception-aware viewpoint metric function that is based on geometry information，structure information and aesthetic information was defined. Secondly，a multi-view objective function was modelled and optimized to obtain a multi-view set by using the simulated annealing algorithm. Extensive experiments show that the proposed method can adaptively obtain a set of all-sided and artistic rendering images for multi-view rendering optimization.

Key words: indoor scene, multi-view rendering, simulated annealing

中图分类号:

TP391.41

汲梦宇，刘利刚. 基于感知的室内场景的多视点渲染优化[J]. 中国科学技术大学学报, 2018, 48(2): 140-147.

JI Mengyu,LIU Ligang. Perception-aware multi-view rendering optimization for indoor scenes[J]. Journal of University of Science and Technology of China, 2018, 48(2): 140-147.

参考文献

［1］
PLEMENOS D, BENAYADA M. Intelligent display in scene modeling new techniques to automatically compute good views[C]// International Conference GraphiCon 1996. 1996, 96: 1-5.
[2] VZQUEZ P P, FEIXAS M, SBERT M, et al. Viewpoint selection using viewpoint entropy[C]// VMV 2001, Stuttgart, Germany. 2001, 1: 273-280.
[3] VIEIRA T, BORDIGNON A, PEIXOTO A, et al. Learning good views through intelligent galleries[J]. Computer Graphics Forum, 2009, 28(2): 717-726.
[4] PAGE D L, KOSCHAN A F, SUKUMAR S R, et al. Shape analysis algorithm based on information theory[C]// Proceedings 2003 International Conference on Image Processing. IEEE, 2003: I-229-I-232.
[5] PODOLAK J, SHILANE P, GOLOVINSKIY A, et al. A planar-reflective symmetry transform for 3D shapes[J]. ACM Transactions on Graphics (TOG), 2006, 25(3): 549-559.
[6] LEE C H, VARSHNEY A, JACOBS D W. Mesh saliency[J]. ACM Transactions on Graphics (TOG), 2005, 24(3): 659-666.
[7] LEIFMAN G, SHTROM E, TAL A. Surface regions of interest for viewpoint selection[C]// Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2012: 414-421.
[8] MORTARA M, SPAGNUOLO M. Semantics-driven best view of 3D shapes[J]. Computers & Graphics, 2009, 33(3): 280-290.
[9] GOOCH B, REINHARD E, MOULDING C, et al. Artistic composition for image creation[M]// Rendering Techniques 2001. Vienna: Springer, 2001: 83-88.
[10] LIU H, ZHANG L, HUANG H. Web-image driven best views of 3D shapes[J]. The Visual Computer, 2012, 28(3): 279-287.
[11] SECORD A, LU J, FINKELSTEIN A, et al. Perceptual models of viewpoint preference[J]. ACM Transactions on Graphics (TOG), 2011, 30(5): No. 109.
[12] SOKOLOV D, PLEMENOS D, TAMINE K. Viewpoint quality and global scene exploration strategies[C]// GRAPP 2006. Trier, Germany: dblp, 2006: 184-191.
[13] BRATKOVA M, THOMPSON W B, SHIRLEY P. Automatic views of natural scenes[C]// Proceedings of the 5th Eurographics Conference on Computational Aesthetics in Graphics, Visualization and Imaging. Switzerland: Eurographics Association Aire-la-Ville, 2009: 33-40.
[14] ZHANG L, LIU H, HUANG H. What’re in a scene? Towards the computational best view of 3D scene[J]. Advanced Science Letters, 2012, 10(1): 465-471.
[15] LIU T, MCCANN J, LI W, et al. Composition-aware scene optimization for product images[J]. Computer Graphics Forum (Proc Eurographics 2015), 2015, 34(2): 13-24.
[16] LOW K L, LASTRA A. An adaptive hierarchical next-best-view algorithm for 3D reconstruction of indoor scenes[C]// Proceedings of 14th Pacific Conference on Computer Graphics and Applications, Taipei, China. 2006: 1-8.
[17] WU S, SUN W, LONG P, et al. Quality-driven poisson-guided autoscanning[J]. ACM Transactions on Graphics (TOG), 2014, 33(6): No.203.
[18] DEBAQUE B, JEDIDI R, PREVOST D. Optimal video camera network deployment to support security monitoring[C]// Proceedings of 12th International Conference on Information Fusion. IEEE, 2009: 1730-1736.
[19] URRUTIA J. Art gallery and illumination problems[J]. Handbook of Computational Geometry, 2000, 1(1): 973-1027.
[20] GONZALEZ-BARBOSA J J, GARCA-RAMREZ T, SALAS J, et al. Optimal camera placement for total coverage[C]// Proceedings of the 2009 IEEE international conference on Robotics and Automation. IEEE, 2009: 844-848.
[21] BECKER E, GUERRA-FILHO G, MAKEDON F. Automatic sensor placement in a 3D volume[C]// Proceedings of the 2nd International Conference on PErvasive Technologies Related to Assistive Environments. New York: ACM, 2009: 36.
[22] AMRIKI K A, ATREY P K. Bus surveillance: how many and where cameras should be placed[J]. Multimedia tools and Applications, 2014, 71(3): 1051-1085.
[23] FISHER M, SAVVA M, HANRAHAN P. Characterizing structural relationships in scenes using graph kernels[J]. ACM Transactions on Graphics, 2011, 30(4): No.34.
[24] LIU L, CHEN R, WOLF L, et al. Optimizing photo composition[J]. Computer Graphics Forum, 2010, 29(2): 469-478.
[25] HWANG C R. Simulated annealing: Theory and applications[J]. Acta Applicandae Mathematicae, 1988, 12(1): 108-111.
[26] FISHER M, RITCHIE D, SAVVA M, et al. Example-based synthesis of 3D object arrangements[J]. ACM Transactions on Graphics, 2012, 31(6): 135.
[27] Google. 3D Warehouse [DB/OL]. [2016-12-01] https://3dwarehouse.sketchup.com/.
[28] 酷家乐.优秀设计[EB/OL]. [2016-12-01] http://www.kujiale.com/design.

()
(

基于感知的室内场景的多视点渲染优化

Perception-aware multi-view rendering optimization for indoor scenes

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价