基于3D空间组件提取和排列的古建筑重建图像方法

Divya Udayanj; Hyung Seokkim; Jeein Kim

doi:10.1631/FITEE.1400141

Your Location：

Home >

Browse articles >

基于3D空间组件提取和排列的古建筑重建图像方法

计算机与自动化 | Updated：2022-06-06

- 基于3D空间组件提取和排列的古建筑重建图像方法
  Enhanced Publication
- An image-based approach to the reconstruction of ancient architectures by extracting and arranging 3D spatial components∗
- 信息与电子工程前沿（英文） 2015年16卷第1期页码：12-27
- Affiliations：
  
  1.Internet and Multimedia Engineering, Konkuk University, Seoul 143-701,Korea
  2.Department of Advanced Technology Fusion, Konkuk University, Seoul 143-701,Korea
- Author bio：
  
  ‡Corresponding Author
- Funds：
- DOI：10.1631/FITEE.1400141
  中图分类号：
- 纸质出版日期：2015-01，
  
  收稿日期：2014-04-20，
  
  修回日期：2014-12-10，
  
  录用日期：2014-08-24
- Accepted：
Scan QR Code
基于3D空间组件提取和排列的古建筑重建图像方法[J]. 信息与电子工程前沿（英文）, 2015,16(1):12-27.

DIVYA UDAYANJ, HYUNG SEOKKIM, JEEIN KIM. An image-based approach to the reconstruction of ancient architectures by extracting and arranging 3D spatial components∗. [J]. Frontiers of information technology & electronic engineering, 2015, 16(1): 12-27.
基于3D空间组件提取和排列的古建筑重建图像方法[J]. 信息与电子工程前沿（英文）, 2015,16(1):12-27. DOI： 10.1631/FITEE.1400141.

DIVYA UDAYANJ, HYUNG SEOKKIM, JEEIN KIM. An image-based approach to the reconstruction of ancient architectures by extracting and arranging 3D spatial components∗. [J]. Frontiers of information technology & electronic engineering, 2015, 16(1): 12-27. DOI： 10.1631/FITEE.1400141.

摘要

目的

利用单一图像重建古建筑，简化从2D照片恢复3D几何结构方法中无穷解的情况。该方法可以应用于观光、游戏、娱乐业中的古迹恢复。

创新

简化从2D照片恢复3D几何结构过程中无穷解的情况。对特定建筑风格生成的组件库可以应用于相同风格的其它古建筑的重建。

方法

本文主要以泰姬陵为例分析。首先，沿边界多面体和多面体之间的邻近关系利用合适的局部平面基元自动重建初始模型。然后，利用建模软件人工推断装配并调整模型3D组件获取最终重建模型。以Mughal风格的三个著名古建筑为例，测试基于前视图的模型重建（图10-12）。

结论

对图像组件的分层分析有助简化从2D照片恢复3D几何结构过程中无穷解的情况。对特定建筑风格生成的组件库可以应用于相同风格的其它古建筑的重建。对三个Mughal风格的三个古建筑进行模型重建，结果表明所提方法的有效性。

Abstract

The objective of this research is the rapid reconstruction of ancient buildings of historical importance using a single image. The key idea of our approach is to reduce the inﬁnite solutions that might otherwise arise when recovering a 3D geometry from 2D photographs. The main outcome of our research shows that the proposed methodology can be used to reconstruct ancient monuments for use as proxies for digital eﬀects in applications such as tourism

games

and entertainment

which do not require very accurate modeling. In this article

we consider the reconstruction of ancient Mughal architecture including the Taj Mahal. We propose a modeling pipeline that makes an easy reconstruction possible using a single photograph taken from a single view

without the need to create complex point clouds from multiple images or the use of laser scanners. First

an initial model is automatically reconstructed using locally ﬁtted planar primitives along with their boundary polygons and the adjacency relation among parts of the polygons. This approach is faster and more accurate than creating a model from scratch because the initial reconstruction phase provides a set of structural information together with the adjacency relation

which makes it possible to estimate the approximate depth of the entire structural monument. Next

we use manual extrapolation and editing techniques with modeling software to assemble and adjust diﬀerent 3D components of the model. Thus

this research opens up the opportunity for the present generation to experience remote sites of architectural and cultural importance through virtual worlds and real-time mobile applications. Variations of a recreated 3D monument to represent an amalgam of various cultures are targeted for future work.

关键词

数字重建3D虚拟世界3D空间组件视觉场景理解

Keywords

Digital reconstruction3D virtual world3D spatial componentsVision and scene understanding

references

S AlHalawani, YL Yang, H Liu, 等. Inter- active facades analysis and synthesis of semi-regular facades. Comput Graph Forum, 2013. 32(2pt2):215-224. DOI:10.1111/cgf.12041http://doi.org/10.1111/cgf.12041.

F Bao, DM Yan, NJ Mitra, 等. Generating and exploring good building layouts. ACM Trans Graph, 2013. 32(4):122.1-12210. DOI:10.1145/2461912.2461977http://doi.org/10.1145/2461912.2461977.

H Bay, T Tuytelaars, L van Gool. SURF: speeded up robust features. 2006. Proc. 9th European Conf. on Computer Vision. 404-417. DOI:10.1007/11744023_32http://doi.org/10.1007/11744023_32.

M Bokeloh, A Berner, M Wand, 等. Symmetry detection using feature lines. Comput Graph Forum, 2009. 28(2):697-706. DOI:10.1111/j.1467-8659.2009.01410.xhttp://doi.org/10.1111/j.1467-8659.2009.01410.x.

D Ceylan, NJ Mitra, H Li, 等. Factored facade acquisition using symmetric line arrangements. Comput Graph Forum, 2012. 31(2pt3):671-680. DOI:10.1111/j.1467-8659.2012.03046.xhttp://doi.org/10.1111/j.1467-8659.2012.03046.x.

D Ceylan, NJ Mitra, Y Zheng, 等. Coupled structure-from-motion and 3D symmetry detection for urban facades. ACM Trans Graph, 2014. 33(1):2.1-215. DOI:10.1145/2517348http://doi.org/10.1145/2517348.

E Chen, L Williams. View interpolation for im- age synthesis. 1993. Proc. 20th Annual Conf. on Com- puter Graphics and Interative Techniques. 279-288. DOI:10.1145/166117.166153http://doi.org/10.1145/166117.166153.

T Chen, Z Zhu, A Shamir, 等. 3-Sweep: ex- truding editable objects from a single photo. ACM Trans Graph, 2013. 32(6):195.1-19510. DOI:10.1145/2508363.2508378http://doi.org/10.1145/2508363.2508378.

A Çıçek, M Gülesın. Reconstruction of 3D models from 2D orthographic views using solid extrusion and revolution. J Mater Process Technol, 2004. 152(3):291-298. DOI:10.1016/j.jmatprotec.2004.04.368http://doi.org/10.1016/j.jmatprotec.2004.04.368.

P Cignoni, C Rocchini, R Scopigno. Metro: mea- suring error on simpliﬁed surfaces. Comput Graph Forum, 1998. 17(2):167-174. DOI:10.1111/1467-8659.00236http://doi.org/10.1111/1467-8659.00236.

A Criminisi, I Reid, A Zisserman. Single view metrology. Int J Comput Vis, 2000. 40(2):123-148. DOI:10.1023/A:1026598000963http://doi.org/10.1023/A:1026598000963.

ER Davies. Machine Vision: Theory, Algorithms, Practicalities, 2005. Morgan Kauﬀman Press, San Francisco, USA, .

PE Debevec, CJ Taylor, J Malik. Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach. 1996. Proc. 23rd Annual Conf. on Computer Graphics and Interative Techniques. 11-20. DOI:10.1145/237170.237191http://doi.org/10.1145/237170.237191.

LR Dung, CM Huang, YY Wu. Implementation of RANSAC algorithm for feature-based image registra- tion. J Comput Commun, 2013. 146-50. DOI:10.4236/jcc.2013.16009http://doi.org/10.4236/jcc.2013.16009.

Encyclopedia. Mughal Architecture, Britannica On- line. 2014. Available from http://global.britannica.com/EB checked/topic/396119/Mughal-architecture [Accessed on Dec. 11, 2014]. .

O Faugeras, S Laveau, L Robert. 3-D re- construction of urban scenes from sequences of im- ages. 1995. Automatic Extraction of Man-Made Objects from Aerial and Space Images. 145-168. DOI:10.1007/978-3-0348-9242-1_15http://doi.org/10.1007/978-3-0348-9242-1_15.

PF Felzenszwalb, DP Huttenlochet. Eﬃcient graph- based image segmentation. Int J Comput Vis, 2004. 59(2):167-181. DOI:10.1023/B:VISI.0000022288.19776.77http://doi.org/10.1023/B:VISI.0000022288.19776.77.

JM Frahm, P Fite-Georgel, D Gallup, 等. Build- ing Rome on a cloudless day. 2010. Proc. 11th European Conf. on Computer Vision. 368-381. DOI:10.1007/978-3-642-15561-1_27http://doi.org/10.1007/978-3-642-15561-1_27.

J Garcia-Gago, J Gomez-Lahoz, J Rodríguez-Méndez, 等. Historical single image-based modeling: the case of Gobierna Tower, Zamora (Spain). Remote Sens, 2014. 6(2):1085-1101. DOI:10.3390/rs6021085http://doi.org/10.3390/rs6021085.

S Geman, D Geman. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans Patt Anal Mach Intell, 1984. 6(6):721-741. DOI:10.1109/TPAMI.1984.4767596http://doi.org/10.1109/TPAMI.1984.4767596.

TH Gormen, CE Leiserson, RL Rivest, 等. Introduction to Algorithms, 1990. MIT Press, McGraw-Hill Book Company, New York, USA, .

E Guillou, D Meneveaux, E Maisel, 等. Using vanishing points for camera calibration and coarse 3D reconstruction from a single image. Vis Comput, 2000. 16(7):396-410. DOI:10.1007/PL00013394http://doi.org/10.1007/PL00013394.

D Hoiem, AA Efros, M Hebert. Geometric context from a single image. 2005. Proc. 10th IEEE Int. Conf. on Computer Vision. 654-661. DOI:10.1109/ICCV.2005.107http://doi.org/10.1109/ICCV.2005.107.

BKP Horn. Height and gradient from shading. IntJ Comput Vis, 1990. 5(1):37-75. DOI:10.1007/BF00056771http://doi.org/10.1007/BF00056771.

Y Horry, K Anjyo, K Arai. Tour into the picture: using a spidery mesh interface to make animation from a single image. 1997. Proc. 24th Annual Conf. on Com- puter Graphics and Interactive Techniques. 225-232. DOI:10.1145/258734.258854http://doi.org/10.1145/258734.258854.

S Kang. Depth Painting for Image-Based Rendering Applications. 1998. Technical Report, Compaq Computer Corporation, Cambridge Research Lab. .

S Laveau, O Faugeras. 3D scene representation as a collection of images. 1994. Proc. 12th Int. Conf. on Pat- tern Recognition. 689-691. DOI:10.1109/ICPR.1994.576404http://doi.org/10.1109/ICPR.1994.576404.

D Liebowitz, A Criminisi, A Zisserman. Creating architectural models from images. Comput Graph Forum, 1999. 18(3):39-50. DOI:10.1111/1467-8659.00326http://doi.org/10.1111/1467-8659.00326.

DG Lowe. Distinctive image features from scale- invariant keypoints. Int J Comput Vis, 2004. 60(2):91-110. DOI:10.1023/B:VISI.0000029664.99615.94http://doi.org/10.1023/B:VISI.0000029664.99615.94.

J Ma, JC Chan, F Canters. Fully automatic subpixel image registration of multiangle CHRIS/Proba data. IEEE Trans GeoSci Remote Sens, 2010. 48(7):2829-2839. DOI:10.1109/TGRS.2010.2042813http://doi.org/10.1109/TGRS.2010.2042813.

AM Manferdini. A methodology for the promotion of cultural heritage sites through the use of low-cost technologies and procedures. 2012. Proc. 17th Int. Conf. on 3D Web Technology. 180DOI:10.1145/2338714.2338747http://doi.org/10.1145/2338714.2338747.

L McMillan, G Bishop. Plenoptic modeling: an image-based rendering system. 1995. Proc. 22nd Annual Conf. on Computer Graphics and Interactive Tech- niques. 39-46. DOI:10.1145/218380.218398http://doi.org/10.1145/218380.218398.

NJ Mitra, M Pauly. Symmetry for architectural design. 2008. Advances in Architectural Geometry. 13-16. .

NJ Mitra, M Pauly, M Wand, 等. Symmetry in 3D geometry: extraction and applications. Comput Graph Forum, 2013. 32(6):1-23. DOI:10.1111/cgf.12010http://doi.org/10.1111/cgf.12010.

P Müller, G Zeng, P Wonka, 等. Image-based procedural modeling of facades. ACM Trans Graph, 2007. 26(3):85.1-859. DOI:10.1145/1276377.1276484http://doi.org/10.1145/1276377.1276484.

T Nagai, M Ikehara, A Kurematsu. HMM-based surface reconstruction from single images. Syst Com- put Jpn, 2007. 38(11):80-89. DOI:10.1002/scj.10685http://doi.org/10.1002/scj.10685.

L Nan, A Sharf, H Zhang, 等. SmartBoxes for interactive urban reconstruction. ACM Trans Graph, 2010. 29(4):93.1-9310. DOI:10.1145/1778765.1778830http://doi.org/10.1145/1778765.1778830.

R Nevatia, KR Babu. Linear feature extraction and description. Comput Graph Image Process, 1980. 13(3):257-269. DOI:10.1016/0146-664X(80)90049-0http://doi.org/10.1016/0146-664X(80)90049-0.

BM Oh, M Chen, J Dorsey, 等. Image-based modeling and photo editing. 2001. Proc. 28th Annual Conf. on Computer Graphics and Interactive Tech- niques. 433-442. DOI:10.1145/383259.383310http://doi.org/10.1145/383259.383310.

P Poulin, M Ouimet, MC Frasson. Interactively modeling with photogrammetry. 1998. Proc. Eurograph- ics Workshop on Rendering. 93-104. DOI:10.1007/978-3-7091-6453-2_9http://doi.org/10.1007/978-3-7091-6453-2_9.

T Pylvanainen, J Berclaz, T Korah, 等. 3D city modeling from street-level data for augmented reality applications. 2012. Proc. 2nd Int. Conf. on 3D Imaging, Modeling, Processing, Visualization and Transmission. 238-245. DOI:10.1109/3DIMPVT.2012.19http://doi.org/10.1109/3DIMPVT.2012.19.

F Remondino. Heritage recording and 3D modeling with photogrammetry and 3D scanning. Remote Sens, 2011. 3(6):1104-1138. DOI:10.3390/rs3061104http://doi.org/10.3390/rs3061104.

A Saxena, SH Chung, AY Ng. 3-D depth reconstruction from a single still image. Int J Comput Vis, 2008. 76(1):53-69. DOI:10.1007/s11263-007-0071-yhttp://doi.org/10.1007/s11263-007-0071-y.

A Saxena, M Sun, AY Ng. Make3D: depth perception from a single still image. 2008. Proc. 23rd AAAI Conf. on Artiﬁcial Intelligence. 1571-1576. .

J Shade, S Gortler, L He, 等. Layered depth images. 1998. Proc. 25th AAAI Annual Conf. on Com- puter Graphics and Interactive Techniques. 231-242. DOI:10.1145/280814.280882http://doi.org/10.1145/280814.280882.

CH Shen, H Fu, K Chen, 等. Structure recovery by part assembly. ACM Trans Graph, 2012. 31(6):180.1-18011. DOI:10.1145/2366145.2366199http://doi.org/10.1145/2366145.2366199.

AD Styliadis, LA Sechidis. Photography-based facade recovery & 3D modeling: a CAD application in cultural heritage. J Cult Herit, 2011. 12(3):243-252. DOI:10.1016/j.culher.2010.12.008http://doi.org/10.1016/j.culher.2010.12.008.

BJ Super, AC Bovik. Shape from texture using local spectral moments. IEEE Trans Patt Anal Mach Intell, 1995. 17(4):333-343. DOI:10.1109/34.385983http://doi.org/10.1109/34.385983.

Y Wang, M Olano. A framework for GPU 3D model reconstruction using structure-from-motion. 2011. Proc. 38th Annual Conf. on Computer Graphics and Interactive Techniques. 27-1. DOI:10.1145/2037715.2037748http://doi.org/10.1145/2037715.2037748.

YM Wei, L Kang, B Yang, 等. Applications of structure from motion: a survey. J. Zhejiang Univ.-Sci. C (Comput. &. Electron), 2013. 14(7):486-494[doi:101631/jzusCIDE1302]. .

MD Yang, CF Chao, KS Huang, 等. Image-based 3D scene reconstruction and exploration in augmented reality. Autom Constr, 2013. 3348-60. DOI:10.1016/j.autcon.2012.09.017http://doi.org/10.1016/j.autcon.2012.09.017.

H Zhang, K Xu, W Jiang, 等. Layered anal- ysis of irregular facades via symmetry maximization. ACM Trans Graph, 2013. 32(4):121.1-12110. DOI:10.1145/2461912.2461923http://doi.org/10.1145/2461912.2461923.

L Zhang, G Dugas-Phocion, JS Samson, 等. Single-view modeling of free-form scenes. JVisualComput Animat, 2002. 13(4):225-235. DOI:10.1002/vis.291http://doi.org/10.1002/vis.291.

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据