Abstract
We describe SORGATE, a procedure for extracting geometry and texture from images of solids of revolution (SORs). It uses multivariate optimization to determine the parameters of the camera in order to build the viewing transform, as well as to reconstruct the geometry of the SOR using the silhouette. In addition to individual image analyses, it can use the data extracted from the same SOR viewed from different directions to produce a single, composite texture which can be combined with their blended geometries to produce a reconstructed 3D model. No prior knowledge other than the object’s rotational symmetry is required. Camera viewing parameters are derived directly from the image.
SORGATE is useful when 3D modeling of SORs is needed yet direct measurement the physical objects is infeasible. As it does not require camera calibration, it is also fast, inexpensive, and practical. One use case might be for researchers and curators who wish to display and/or analyze the art on historical vases; metric reconstruction and proper texturing of the objects would allow this without requiring viewing in person.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Due to variations in camera pitch (\(\beta _{\mathrm {cam}}\)), textures need to be aligned vertically as well as horizontally, if only slightly. Figure 8 exaggerates this for illustration.
References
Overbeck Vase, ca 1920 | Antiques Roadshow | PBS (2017). https://image.pbs.org/video-assets/pbs/antiques-roadshow/256002/images/mezzanine_222.jpg.crop.379x212.jpg
Boyer, E., Berger, M.O.: 3D surface reconstruction using occluding contours. Int. J. Comput. Vis. 22(3), 219–233 (1997)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proceedings Eighth IEEE International Conference on Computer Vision (ICCV 2001) 1, pp. 105–112 (2001)
Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. PAMI 8(6), 679–698 (1986)
Chellali, R., Fremont, V., Maaoui, C.: A new approach to 3-D modeling of objects with axial symmetry. IEEE Trans. Ind. Electron. 50(4), 1–7 (2003)
Colombo, C., Del Bimbo, A., Pernici, F.: Uncalibrated 3D metric reconstruction and flattened texture acquisition from a single view of a surface of revolution. In: Proceedings - 1st International Symposium on 3D Data Processing Visualization and Transmission, 3DPVT 2002, vol. 27(1), pp. 277–284 (2002)
Debevec, P.E., Taylor, C.J., Malik, J.: Modeling and Rendering Architecture from Photographs: A hybrid geometry-and image-based approach. Technical report (1996)
Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 476–480 (1999)
Ghosh, S., Das, N., Das, I., Maulik, U.: Understanding deep learning techniques for image segmentation. ACM Comput. Surv. 52, 1–35 (2019)
Goshtasby, A.A.: Image Registration: Principles, Tools and Methods. Springer, London (2012). https://doi.org/10.1007/978-1-4471-2458-0
Jain, A.: Automatic 3D Reconstruction for Symmetric Shapes (2016)
Jolliffe, I.: Principal Component Analysis. Springer, New York (1986). https://doi.org/10.1007/978-1-4757-1904-8
Ledesma, A.: SORGATE: Surface of Revolution Geometry and Texture Extraction. Master’s thesis, May 2021
Liu, C., Hu, W.: Ellipse fitting for imaged cross sections of a surface of revolution. Pattern Recogn. 48(4), 1440–1454 (2015). https://doi.org/10.1016/j.patcog.2014.09.028
Nelder, J.A., Mead, R.: A simplex method for function minimization. Comput. J. 7(4), 308–313 (1965)
Pernici, F.: Two Results in Computer Vision using Projective Geometry. Ph.D. thesis, University of Florence (2005). https://www.micc.unifi.it/pernici/index_files/PhdThesis.pdf
Ponce, J., Chelberg, D., Mann, W.B.: Invariant properties of straight homogeneous generalized cylinders and their contours. IEEE Trans. Pattern Anal. Mach. Intell. 11(9), 951–966 (1989)
Puech, W., Chassery, J.M., Pitas, I.: Cylindrical surface localization in monocular vision. Pattern Recogn. Lett. 18(8), 711–722 (1997)
Rother, C., Kolmogorov, V., Blake, A.: GrabCut. ACM Trans. Graph. 23(3), 309–314 (2004)
Shirley, P., Marschner, S.: Viewing. In: Fundamentals of Computer Graphics, 3rd edn. pp. 141–159. A K Peters/CRC Press, Boca Raton (2009). Chap. 7
Szeliski, R.: Computer Vision: Algorithms and Applications. Springer, London (2011). https://doi.org/10.1007/978-1-84882-935-0
Tsai, R.Y.: A versatile camera calibration techniaue for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses ROGER. IEEE J. Robot. Autom. 3(4), 323–344 (1987)
Ulupinar, F., Nevatia, R.: Shape from contour: straight homogeneous generalized cylinders and constant cross section generalized cylinders. IEEE Trans. Pattern Anal. Mach. Intell. 17(2), 120–135 (1995)
Wong, K.Y.K., Mendonça, P.R., Cipolla, R.: Reconstruction of surfaces of revolution from single uncalibrated views. Image Vis. Comput. 22(10 SPEC. ISS.), 829–836 (2004)
Worring, M., Smeulders, A.W.: Digital curvature estimation. Comput. Vis. Image Underst. 58(3), 366–382 (1993)
Zhang, M., Zheng, Y., Liu, Y.: Using silhouette for pose estimation of object with surface of revolution. In: Proceedings - International Conference on Image Processing, ICIP, pp. 333–336 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ledesma, A., Lewis, R.R. (2021). SORGATE: Extracting Geometry and Texture from Images of Solids of Revolution. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2021. Lecture Notes in Computer Science(), vol 13017. Springer, Cham. https://doi.org/10.1007/978-3-030-90439-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-90439-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90438-8
Online ISBN: 978-3-030-90439-5
eBook Packages: Computer ScienceComputer Science (R0)