Abstract
While multi-view stereo reconstruction of Lambertian surfaces is nowadays highly robust, reconstruction methods based on correspondence search usually fail in the presence of ambiguous information, like in the case of partially reflecting and transparent surfaces. On the epipolar plane images of a 4D light field, however, surfaces like these give rise to overlaid patterns of oriented lines. We show that these can be identified and analyzed quickly and accurately with higher order structure tensors. The resulting method can reconstruct with high precision both the geometry of the surface as well as the geometry of the reflected or transmitted object. Accuracy and feasibility are shown on both ray-traced synthetic scenes and real-world data recorded by our gantry.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Seitz, S., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Proc. International Conference on Computer Vision and Pattern Recognition, pp. 519–528 (2006)
Borga, K.: Estimating multiple depths in semi-transparent stereo images. In: SCIA (1999)
Jin, H., Soatto, S., Yezzi, A.: Multi-view stereo reconstruction of dense shape and complex appearance. International Journal of Computer Vision 63(3), 175–189 (2005)
Tsin, Y., Kang, S., Szeliski, R.: Stereo matching with linear superposition of layers. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(2), 290–301 (2006)
Sinha, S., Kopf, J., Goesele, M., Scharstein, D., Szeliski, R.: Image-based rendering for scenes with reflections. ACM Transactions on Graphics (Proc. SIGGRAPH) 31(4), 100:1–100:10 (2012)
Aach, T., Mota, C., Stuke, I., Muehlich, M., Barth, E.: Analysis of superimposed oriented patterns. IEEE Transactions on Image Processing 15(12), 3690–3700 (2006)
Davis, J., Yang, R., Wang, L.: BRDF invariant stereo using light transport constancy. In: Proc. International Conference on Computer Vision (2005)
Alldrin, N., Zickler, T., Kriegman, D.: Photometric stereo with non-parametric and spatially-varying reflectance. In: Proc. International Conference on Computer Vision and Pattern Recognition (2008)
Ruiters, R., Klein, R.: Heightfield and spatially varying BRDF reconstruction for materials with interreflections. Computer Graphics Forum (Proc. Eurographics) 28(2), 513–522 (2009)
Goldman, D., Curless, B., Hertzmann, A., Seitz, S.: Shape and spatially-varying BRDFs from photometric stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(6), 1060–1071 (2010)
Zickler, T., Belhumeur, P., Kriegman, D.: Helmholtz stereopsis: Exploiting reciprocity for surface reconstruction. International Journal of Computer Vision 49(2–3), 215–227 (2002)
Levin, A., Zomet, A., Weiss, Y.: Separating reflections from a single image using local features. In: Proc. International Conference on Computer Vision and Pattern Recognition (2004)
Levin, A., Weiss, Y.: User assisted separation of reflections from a single image using a sparsity prior. IEEE Transactions on Pattern Analysis and Machine Intelligence (2007)
Bolles, R., Baker, H., Marimont, D.: Epipolar-plane image analysis: An approach to determining structure from motion. International Journal of Computer Vision 1(1), 7–55 (1987)
Wanner, S., Goldluecke, B.: Globally consistent depth labeling of 4D light fields. In: Proc. International Conference on Computer Vision and Pattern Recognition, pp. 41–48 (2012)
Gortler, S., Grzeszczuk, R., Szeliski, R., Cohen, M.: The Lumigraph. In: Proc. SIGGRAPH, pp. 43–54 (1996)
Bigün, J., Granlund, G.H.: Optimal orientation detection of linear symmetry. In: Proc. International Conference on Computer Vision, pp. 433–438 (1987)
Smith, O.: Eigenvalues of a symmetric 3x3 matrix. Communications of the ACMÂ 4(4), 168 (1961)
Chambolle, A.: An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision 20(1-2), 89–97 (2004)
Pock, T., Cremers, D., Bischof, H., Chambolle, A.: Global solutions of variational models with convex regularization. SIAM Journal on Imaging Sciences (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wanner, S., Goldluecke, B. (2013). Reconstructing Reflective and Transparent Surfaces from Epipolar Plane Images. In: Weickert, J., Hein, M., Schiele, B. (eds) Pattern Recognition. GCPR 2013. Lecture Notes in Computer Science, vol 8142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40602-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-40602-7_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40601-0
Online ISBN: 978-3-642-40602-7
eBook Packages: Computer ScienceComputer Science (R0)