Animage-based approach to the reconstruction of ancient architectures by extracting and arranging 3D spatial components

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.

Keywords

Digital reconstruction / 3D virtual world / 3D spatial components / Vision and scene understanding

References

[1] AlHalawani, S., Yang, Y.L., Liu, H., , 2013. Interactive facades analysis and synthesis of semi-regular facades. Comput. Graph. Forum, 32(2pt2): 215−224.

[2] Bao, F., Yan, D.M., Mitra, N.J., , 2013. Generating and exploring good building layouts. ACM Trans. Graph., 32(4): 122.1−122.10.

[3] Bay, H., Tuytelaars, T., van Gool, L., 2006. SURF: speeded up robust features. Proc. 9th European Conf. on Computer Vision, p.404−417.

[4] Bokeloh, M., Berner, A., Wand, M., , 2009. Symmetry detection using feature lines. Comput. Graph. Forum, 28(2): 697−706.

[5] Ceylan, D., Mitra, N.J., Li, H., , 2012. Factored facade acquisition using symmetric line arrangements. Comput. Graph. Forum, 31(2pt3): 671−680.

[6] Ceylan, D., Mitra, N.J., Zheng, Y., , 2014. Coupled structure-from-motion and 3D symmetry detection for urban facades. ACM Trans. Graph., 33(1): 2.1−2.15.

[7] Chen, E., Williams, L., 1993. View interpolation for image synthesis. Proc. 20th Annual Conf. on Computer Graphics and Interative Techniques, p.279−288.

[8] Chen, T., Zhu, Z., Shamir, A., , 2013. 3-Sweep: extruding editable objects from a single photo. ACM Trans. Graph., 32(6): 195.1−195.10.

[9] Çıçek, A., Gülesın, M., 2004. Reconstruction of 3D models from 2D orthographic views using solid extrusion and revolution. J. Mater. Process. Technol., 152(3): 291−298.

[10] Cignoni, P., Rocchini, C., Scopigno, R., 1998. Metro: measuring error on simplified surfaces. Comput. Graph. Forum, 17(2):167−174.

[11] Criminisi, A., Reid, I., Zisserman, A., 2000. Single view metrology. Int. J. Comput. Vis., 40(2):123−148.

[12] Davies, E.R., 2005. Machine Vision: Theory, Algorithms, Practicalities. Morgan Kauffman Press, San Francisco, USA.

[13] Debevec, P.E., Taylor, C.J., Malik, J., 1996. Modeling and rendering architecture from photographs: a hybrid geometry- and image-based approach. Proc. 23rd Annual Conf. on Computer Graphics and Interative Techniques, p.11−20.

[14] Dung, L.R., Huang, C.M., Wu, Y.Y., 2013. Implementation of RANSAC algorithm for feature-based image registration. J. Comput. Commun., 1: 46−50.

[15] Encyclopedia, 2014. Mughal Architecture, Britannica Online. Available from https://www.britannica.com/art/Mughal-architecture [Accessed on 2014-Dec].

[16] Faugeras, O., Laveau, S., Robert, L., 1995. 3-D reconstruction of urban scenes from sequences of images. Automatic Extraction of Man-Made Objects from Aerial and Space Images, p.145−168.

[17] Felzenszwalb, P.F., Huttenlochet, D.P., 2004. Efficient graphbased image segmentation. Int. J. Comput. Vis., 59(2): 167−181.

[18] Frahm, J.M., Fite-Georgel, P., Gallup, D., , 2010. Building Rome on a cloudless day. Proc. 11th European Conf. on Computer Vision, p. 368−381.

[19] Garcia-Gago, J., Gomez-Lahoz, J., Rodriguez-Mendez, J., , 2014. Historical single image-based modeling: the case of Gobierna Tower, Zamora (Spain). Remote Sens., 6(2): 1085−1101.

[20] Geman, S., Geman, D., 1984. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans. Patt. Anal. Mach. Intell., 6(6): 721−741.

[21] Gormen, T.H., Leiserson, C.E., Rivest, R.L., , 1990. Introduction to Algorithms. MIT Press, McGraw-Hill Book Company, New York, USA.

[22] Guillou, E., Meneveaux, D., Maisel, E., , 2000. Using vanishing points for camera calibration and coarse 3D reconstruction from a single image. Vis. Comput., 16(7): 396−410.

[23] Hoiem, D., Efros, A.A., Hebert, M., 2005. Geometric context from a single image. Proc. 10th IEEE Int. Conf. on Computer Vision, p. 654−661.

[24] Horn, B.K.P., 1990. Height and gradient from shading. Int. J. Comput. Vis., 5(1): 37−75.

[25] Horry, Y., Anjyo, K., Arai, K., 1997. Tour into the picture: using a spidery mesh interface to make animation from a single image. Proc. 24th Annual Conf. on Computer Graphics and Interactive Techniques, p.225−232.

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

[27] Laveau, S., Faugeras, O., 1994. 3D scene representation as a collection of images. Proc. 12th Int. Conf. on Pattern Recognition, p.689−691.

[28] Liebowitz, D., Criminisi, A., Zisserman, A., 1999. Creating architectural models from images. Comput. Graph. Forum, 18(3): 39−50.

[29] Lowe, D.G., 2004. Distinctive image features from scaleinvariant keypoints. Int. J. Comput. Vis., 60(2): 91−110.

[30] Ma, J., Chan, J.C., Canters, F., 2010. Fully automatic subpixel image registration of multiangle CHRIS/Proba data. IEEE Trans. GeoSci. Remote Sens., 48(7): 2829−2839.

[31] Manferdini, A.M., 2012. A methodology for the promotion of cultural heritage sites through the use of low-cost technologies and procedures. Proc. 17th Int. Conf. on 3D Web Technology, p.180.

[32] McMillan, L., Bishop, G., 1995. Plenoptic modeling: an image-based rendering system. Proc. 22nd Annual Conf. on Computer Graphics and Interactive Techniques, p.39−46.

[33] Mitra, N.J., Pauly, M., 2008. Symmetry for architectural design. Advances in Architectural Geometry, p.13−16.

[34] Mitra, N.J., Pauly, M., Wand, M., , 2013. Symmetry in 3D geometry: extraction and applications. Comput. Graph. Forum, 32(6): 1−23.

[35] Muller, P., Zeng, G., Wonka, P., , 2007. Image-based procedural modeling of facades. ACM Trans. Graph., 26(3): 85.1−85.9.

[36] Nagai, T., Ikehara, M., Kurematsu, A., 2007. HMM-based surface reconstruction from single images. Syst. Comput. Jpn., 38(11): 80−89.

[37] Nan, L., Sharf, A., Zhang, H., , 2010. SmartBoxes for interactive urban reconstruction. ACM Trans. Graph., 29(4): 93.1−93.10.

[38] Nevatia, R., Babu, K.R., 1980. Linear feature extraction and description. Comput. Graph. Image Process., 13(3): 257−269.

[39] Oh, B.M., Chen, M., Dorsey, J., , 2001. Image-based modeling and photo editing. Proc. 28th Annual Conf. on Computer Graphics and Interactive Techniques, p.433−442.

[40] Poulin, P., Ouimet, M., Frasson, M.C., 1998. Interactively modeling with photogrammetry. Proc. Eurographics Workshop on Rendering, p.93−104.

[41] Pylvanainen, T., Berclaz, J., Korah, T., , 2012. 3D city modeling from street-level data for augmented reality applications. Proc. 2nd Int. Conf. on 3D Imaging, Modeling, Processing, Visualization and Transmission, p.238−245.

[42] Remondino, F., 2011. Heritage recording and 3D modeling with photogrammetry and 3D scanning. Remote Sens., 3(6): 1104−1138.

[43] Saxena, A., Chung, S.H., Ng, A.Y., 2008a. 3-D depth reconstruction from a single still image. Int. J. Comput. Vis., 76(1): 53−69.

[44] Saxena, A., Sun, M., Ng, A.Y., 2008b. Make3D: depth perception from a single still image. Proc. 23rd AAAI Conf. on Artificial Intelligence, p.1571−1576.

[45] Shade, J., Gortler, S., He, L., , 1998. Layered depth images. Proc. 25th AAAI Annual Conf. on Computer Graphics and Interactive Techniques, p.231−242.

[46] Shen, C.H., Fu, H., Chen, K., , 2012. Structure recovery by part assembly. ACM Trans. Graph., 31(6): 180.1−180.11.

[47] Styliadis, A.D., Sechidis, L.A., 2011. Photography-based facade recovery & 3D modeling: a CAD application in cultural heritage. J. Cult. Herit., 12(3): 243−252.

[48] Super, B.J., Bovik, A.C., 1995. Shape from texture using local spectral moments. IEEE Trans. Patt. Anal. Mach. Intell., 17(4): 333−343.

[49] Wang, Y., Olano, M., 2011. A framework for GPU 3D model reconstruction using structure-from-motion. Proc. 38th Annual Conf. on Computer Graphics and Interactive Techniques, p.27.1.

[50] Wei, Y.M., Kang, L., Yang, B., , 2013. Applications of structure from motion: a survey. J. Zhejiang Univ.-Sci. C (Comput. & Electron.), 14(7): 486−494.

[51] Yang, M.D., Chao, C.F., Huang, K.S., , 2013. Imagebased 3D scene reconstruction and exploration in augmented reality. Autom. Constr., 33: 48−60.

[52] Zhang, H., Xu, K., Jiang, W., , 2013. Layered analysis of irregular facades via symmetry maximization. ACM. Trans. Graph., 32(4): 121.1−121.10.

[53] Zhang, L., Dugas-Phocion, G., Samson, J.S., , 2002. Single-view modeling of free-form scenes. J. Visual. Comput. Animat., 13(4): 225−235.

RIGHTS & PERMISSIONS

2015 Higher Education Press and Springer-Verlag Berlin Heidelberg