Abstract
In this work, we propose a method to recover the shape of a complex mirror surface from a single image with un-calibrated environment. A complex mirror surface reflects the same environment feature at multiple surface points. These static reflection correspondences (SRCs) can be detected with SIFT (or its variations) and provide important visual cue of the surface shape. The detected SRCs are clustered by a bipartite graph partition method so that each cluster of SRCs is within either elliptic or hyperbolic surface regions. The surface region is then further segmented by a Voronoi diagram of the SRCs. Within each Voronoi cell, the surface is approximated by a local quadric model. Assuming orthographic projection and distant environment, the SRCs of an environment feature share the same surface gradient, which provides a major constraint to the surface shape. Along with the smoothness constraints, the surface shape can be recovered with an optimization method. Synthesized and physical experiments support our proposed method.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Adato, Y., Vasilyev, Y., Zickler, T., et al.: Shape from specular flow. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(11), 2054–2070 (2010)
Agrawal, A., Raskar, R., Chellappa, R.: Surface reconstruction from gradient fields via gradient transformations. IJCV 5 (2009)
Blake, A., Brelstaff, G.: Specular Stereo. IJCAI, 973–976 (1985)
Balzer, J., Hofer, S., Beyerer, J.: Multiview specular stereo reconstruction of large mirror surfaces. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2537–2544. IEEE (2011)
Bonfort, T., Sturm, P.: Voxel carving for specular surfaces. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, pp. 591–596. IEEE (2003)
Bruce, J.W., Giblin, P.J.: Curves and Singularities: a geometrical introduction to singularity theory. Cambridge University Press (1992)
Fleming, R.W., Torralba, A., Adelson, E.H.: Specular reflections and the perception of shape[J]. Journal of Vision 4(9), 10 (2004)
Halstead, M.A., Barsky, B.A., Klein, S.A., et al.: Reconstructing curved surfaces from specular reflection patterns using spline surface fitting of normals. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, pp. 335–342. ACM (1996)
Kutulakos, K.N., Steger, E.: A theory of refractive and specular 3d shape by light-path triangulation. International Journal of Computer Vision 76(1), 13–29 (2008)
Liu, M., Wong, K.Y.K., Dai, Z., et al.: Pose estimation from reflections for specular surface recovery. In: 2011 IEEE International Conference on Computer Vision (ICCV), pp. 579–586. IEEE (2011)
Liu, M., Hartley, R., Salzmann, M.: Mirror surface reconstruction from a single image. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 129–136. IEEE (2013)
Nehab, D., Weyrich, T., Rusinkiewicz, S.: Dense 3d reconstruction from specularity consistency. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)
Oren, M., Nayar, S.K.: A theory of specular surface geometry. International Journal of Computer Vision 24(2), 105–124 (1997)
Rozenfeld, S., Shimshoni, I., Lindenbaum, M.: Dense mirroring surface recovery from 1d homographies and sparse correspondences. IEEE Transactions on attern Analysis and Machine Intelligence 33(2), 325–337 (2011)
Sankaranarayanan, A.C., Veeraraghavan, A., Tuzel, O., et al.: Specular surface reconstruction from sparse reflection correspondences. In: IEEE Conference on omputer Vision and Pattern Recognition (CVPR), pp. 1245–1252. IEEE (2010)
Sankaranarayanan, s.C., Veeraraghavan, A., Tuzel, O., Agrawal, A.: Image invariants for smooth reflective surfaces. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part II. LNCS, vol. 6312, pp. 237–250. Springer, Heidelberg (2010)
Savarese, S., Chen, M., Perona, P.: Local shape from mirror reflections. International Journal of Computer Vision 64(1), 31–67 (2005)
Solem, J.E., Aanæs, H., Heyden, A.: A variational analysis of shape from specularities using sparse data. In: Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 3DPVT 2004, pp. 26–33. IEEE (2004)
Tappen, M.F.: Recovering shape from a single image of a mirrored surface from curvature constraints. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2545–2552. IEEE (2011)
Tarini, M., Lensch, H., Goesele, M., et al.: 3D acquisition of mirroring objects using striped patterns. Graphical Models 67(4), 233–259 (2005)
Vasilyev, Y., Adato, Y., Zickler, T., et al.: Dense specular shape from multiple specular flows. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)
Zisserman, A., Giblin, P., Blake, A.: The information available to a moving observer from specularities. Image and vision computing 7(1), 38–42 (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Li, H., Song, T., Wu, Z., Ma, J., Ding, G. (2014). Reconstruction of a Complex Mirror Surface from a Single Image. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2014. Lecture Notes in Computer Science, vol 8887. Springer, Cham. https://doi.org/10.1007/978-3-319-14249-4_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-14249-4_38
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14248-7
Online ISBN: 978-3-319-14249-4
eBook Packages: Computer ScienceComputer Science (R0)