Abstract
The ability to digitise real objects is fundamental in applications such as film post-production, cultural heritage preservation and video game development. While many existing modelling techniques achieve impressive results, they are often reliant on assumptions such as prior knowledge of the scene’s surface reflectance. This considerably restricts the range of scenes that can be reconstructed, as these assumptions are often violated in practice. One technique that allows surface reconstruction regardless of the scene’s reflectance model is Helmholtz Stereopsis (HS). However, to date, research on HS has mostly been limited to 2.5D scene reconstruction. In this paper, a framework is introduced to perform full 3D HS using Markov Random Field (MRF) optimisation for the first time. The paper introduces two complementary techniques. The first approach computes multiple 2.5D reconstructions from a small number of viewpoints and fuses these together to obtain a complete model, while the second approach directly reasons in the 3D domain by performing a volumetric MRF optimisation. Both approaches are based on optimising an energy function combining an HS confidence measure and normal consistency across the reconstructed surface. The two approaches are evaluated on both synthetic and real scenes, measuring the accuracy and completeness obtained. Further, the effect of noise on modelling accuracy is experimentally evaluated on the synthetic dataset. Both techniques achieve sub-millimetre accuracy and exhibit robustness to noise. In particular, the method based on full 3D optimisation is shown to significantly outperform the other approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Addari, G., Guillemaut, J.Y.: An MRF optimisation framework for full 3D Helmholtz stereopsis. In: 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pp. 725–736, January 2019. https://doi.org/10.5220/0007407307250736
Andres, B., Kappes, J.H., Beier, T., Köthe, U., Hamprecht, F.A.: The lazy flipper: efficient depth-limited exhaustive search in discrete graphical models. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, Part VII, vol. 7578, pp. 154–166. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33786-4_12
Besag, J.: On the statistical analysis of dirty pictures. J. Roy. Stat. Soc. B 48(3), 48–259 (1986)
Chandraker, M., Bai, J., Ramamoorthi, R.: On differential photometric reconstruction for unknown, isotropic brdfs. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2941–2955 (2013). https://doi.org/10.1109/TPAMI.2012.217
Delaunoy, A., Prados, E., Belhumeur, P.N.: Towards full 3D Helmholtz stereovision algorithms. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, Part I, vol. 6492, pp. 39–52. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-19315-6_4
Goldman, D.B., Curless, B., Hertzmann, A., Seitz, S.M.: Shape and spatially-varying BRDFs from photometric stereo. IEEE Trans. Pattern Anal. Mach. Intell. 32(6), 1060–1071 (2010). https://doi.org/10.1109/TPAMI.2009.102. http://dx.doi.org/10.1109/TPAMI.2009.102
Guillemaut, J., Drbohlav, O., Illingworth, J., Sára, R.: A maximum likelihood surface normal estimation algorithm for Helmholtz stereopsis. In: VISAPP 2008: Proceedings of the Third International Conference on Computer Vision Theory and Applications 2008, vol. 2, pp. 352–359 (2008)
Guillemaut, J.Y., Drbohlav, O., Sára, R., Illingworth, J.: Helmholtz stereopsis on rough and strongly textured surfaces. In: 3DPVT, pp. 10–17. IEEE Computer Society (2004)
Han, T., Shen, H.: Photometric stereo for general BRDFs via reflection sparsity modeling. IEEE Trans. Image Process. 24(12), 4888–4903 (2015). https://doi.org/10.1109/TIP.2015.2471081
Ishikawa, H.: Higher-order clique reduction without auxiliary variables. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1362–1369, June 2014. https://doi.org/10.1109/CVPR.2014.177
Janko, Z., Drbohlav, O., Sara, R.: Radiometric calibration of a Helmholtz stereo rig. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. I-166, January 2004
Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: Proceedings of the Fourth Eurographics Symposium on Geometry Processing, SGP 2006, pp. 61–70. Eurographics Association (2006). http://dl.acm.org/citation.cfm?id=1281957.1281965
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE Trans. Pattern Anal. Mach. Intell. 28(10), 1568–1583 (2006). https://doi.org/10.1109/TPAMI.2006.200. http://dx.doi.org/10.1109/TPAMI.2006.200
Krishnamurthy, V., Levoy, M.: Fitting smooth surfaces to dense polygon meshes. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1996, pp. 313–324 (1996). https://doi.org/10.1145/237170.237270, http://doi.acm.org/10.1145/237170.237270
Laurentini, A.: The visual hull concept for silhouette-based image understanding. IEEE Trans. Pattern Anal. Mach. Intell. 16(2), 150–162 (1994). https://doi.org/10.1109/34.273735. http://dx.doi.org/10.1109/34.273735
Lewis, R.R.: Making shaders more physically plausible. In: Fourth Eurographics Workshop on Rendering, pp. 47–62 (1994)
Liang, C., Wong, K.Y.K.: 3D reconstruction using silhouettes from unordered viewpoints. Image Vision Comput. 28(4), 579–589 (2010). https://doi.org/10.1016/j.imavis.2009.09.012. http://dx.doi.org/10.1016/j.imavis.2009.09.012
Lombardi, S., Nishino, K.: Radiometric scene decomposition: scene reflectance, illumination, and geometry from RGB-D images. CoRR abs/1604.01354 (2016). http://arxiv.org/abs/1604.01354
Magda, S., Kriegman, D.J., Zickler, T.E., Belhumeur, P.N.: Beyond lambert: reconstructing surfaces with arbitrary brdfs. In: ICCV (2001)
Nasrin, R., Jabbar, S.: Efficient 3D visual hull reconstruction based on marching cube algorithm. In: 2015 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), pp. 1–6, March 2015. https://doi.org/10.1109/ICIIECS.2015.7193189
Nishino, K.: Directional statistics BRDF model. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 476–483, September 2009. https://doi.org/10.1109/ICCV.2009.5459255
Oxholm, G., Nishino, K.: Shape and reflectance estimation in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 376–389 (2016). https://doi.org/10.1109/TPAMI.2015.2450734
Roubtsova, N., Guillemaut, J.: Bayesian Helmholtz stereopsis with integrability prior. IEEE Trans. Pattern Anal. Mach. Intell. 40(9), 2265–2272 (2018). https://doi.org/10.1109/TPAMI.2017.2749373
Roubtsova, N., Guillemaut, J.Y.: Colour Helmholtz stereopsis for reconstruction of dynamic scenes with arbitrary unknown reflectance. Int. J. Comput. Vision 124(1), 18–48 (2017). https://doi.org/10.1007/s11263-016-0951-0
Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, vol. 1, pp. 519–528. IEEE Computer Society, Washington, DC, USA (2006). https://doi.org/10.1109/CVPR.2006.19, http://dx.doi.org/10.1109/CVPR.2006.19
Szeliski, R., et al.: A comparative study of energy minimization methods for markov random fields with smoothness-based priors. IEEE Trans. Pattern Anal. Mach. Intell. 30(6), 1068–1080 (2008)
Tu, P., Mendonca, P.R.S.: Surface reconstruction via Helmholtz reciprocity with a single image pair. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings, vol. 1, pp. I-541–I-547, June 2003. https://doi.org/10.1109/CVPR.2003.1211401
Turk, G., Levoy, M.: Zippered polygon meshes from range images. In: Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1994, pp. 311–318. ACM, New York (1994). https://doi.org/10.1145/192161.192241, http://doi.acm.org/10.1145/192161.192241
Vogiatzis, G., Hernandez, C., Cipolla, R.: Reconstruction in the round using photometric normals and silhouettes. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, vol. 2, pp. 1847–1854. IEEE Computer Society, Washington, DC, USA (2006). https://doi.org/10.1109/CVPR.2006.245, http://dx.doi.org/10.1109/CVPR.2006.245
Von Helmholtz, H., Southall, J.P.: Helmholtz’s treatise on physiological optics, vol. 1. Optical Society of America, New York (1924). Translation
Weinmann, M., Ruiters, R., Osep, A., Schwartz, C., Klein, R.: Fusing structured light consistency and Helmholtz normals for 3D reconstruction. In: British Machine Vision Conference, September 2012. accepted for publication
Woodham, R.J.: Photometric method for determining surface orientation from multiple images. Opt. Eng. 19(1), 191139 (1980). https://doi.org/10.1117/12.7972479. http://dx.doi.org/10.1117/12.7972479
Zickler, T.E., Ho, J., Kriegman, D.J., Ponce, J., Belhumeur, P.N.: Binocular Helmholtz stereopsis. In: Proceedings Ninth IEEE International Conference on Computer Vision, vol. 2, pp. 1411–1417, October 2003. https://doi.org/10.1109/ICCV.2003.1238655
Zickler, T.: Reciprocal image features for uncalibrated Helmholtz stereopsis. In: IEEE Computer Vision and Pattern Recognitiion, pp. II: 1801–1808 (2006). http://www.cs.virginia.edu/~mjh7v/bib/Zickler06.pdf
Zickler, T.E., Belhumeur, P.N., Kriegman, D.J.: Helmholtz stereopsis: exploiting reciprocity for surface reconstruction. Int. J. Comput. Vision 49(2), 215–227 (2002). https://doi.org/10.1023/A:1020149707513. http://dx.doi.org/10.1023/A:1020149707513
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Addari, G., Guillemaut, JY. (2020). An MRF Optimisation Framework for Full 3D Reconstruction of Scenes with Complex Reflectance. In: Cláudio, A., et al. Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2019. Communications in Computer and Information Science, vol 1182. Springer, Cham. https://doi.org/10.1007/978-3-030-41590-7_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-41590-7_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41589-1
Online ISBN: 978-3-030-41590-7
eBook Packages: Computer ScienceComputer Science (R0)