Skip to main content
SpringerLink
Log in

Reconstructing Reflective and Transparent Surfaces from Epipolar Plane Images

  • Conference paper
Pattern Recognition (GCPR 2013)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 8142))

Included in the following conference series:

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

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 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)

    Google Scholar 

  2. Borga, K.: Estimating multiple depths in semi-transparent stereo images. In: SCIA (1999)

    Google Scholar 

  3. 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)

    Article  Google Scholar 

  4. 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)

    Article  Google Scholar 

  5. 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)

    Google Scholar 

  6. 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)

    Article  MathSciNet  Google Scholar 

  7. Davis, J., Yang, R., Wang, L.: BRDF invariant stereo using light transport constancy. In: Proc. International Conference on Computer Vision (2005)

    Google Scholar 

  8. 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)

    Google Scholar 

  9. Ruiters, R., Klein, R.: Heightfield and spatially varying BRDF reconstruction for materials with interreflections. Computer Graphics Forum (Proc. Eurographics) 28(2), 513–522 (2009)

    Article  Google Scholar 

  10. 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)

    Article  Google Scholar 

  11. Zickler, T., Belhumeur, P., Kriegman, D.: Helmholtz stereopsis: Exploiting reciprocity for surface reconstruction. International Journal of Computer Vision 49(2–3), 215–227 (2002)

    Article  MATH  Google Scholar 

  12. 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)

    Google Scholar 

  13. 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)

    Google Scholar 

  14. 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)

    Article  Google Scholar 

  15. 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)

    Google Scholar 

  16. Gortler, S., Grzeszczuk, R., Szeliski, R., Cohen, M.: The Lumigraph. In: Proc. SIGGRAPH, pp. 43–54 (1996)

    Google Scholar 

  17. Bigün, J., Granlund, G.H.: Optimal orientation detection of linear symmetry. In: Proc. International Conference on Computer Vision, pp. 433–438 (1987)

    Google Scholar 

  18. Smith, O.: Eigenvalues of a symmetric 3x3 matrix. Communications of the ACM 4(4), 168 (1961)

    Article  Google Scholar 

  19. Chambolle, A.: An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision 20(1-2), 89–97 (2004)

    MathSciNet  Google Scholar 

  20. Pock, T., Cremers, D., Bischof, H., Chambolle, A.: Global solutions of variational models with convex regularization. SIAM Journal on Imaging Sciences (2010)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Heidelberg Collaboratory for Image Processing, Germany

    Sven Wanner & Bastian Goldluecke

Authors
  1. Sven Wanner
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bastian Goldluecke
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Faculty of Mathematics and Computer Science, Saarland University, Campus E1.7, 66041, Saarbrücken, Germany

    Joachim Weickert

  2. Faculty of Mathematics and Computer Science, Saarland University, Campus E1.3, 66041, Saarbrücken, Germany

    Matthias Hein

  3. Computer Vision and Multimodal Computing, Max-Planck-Institute for Informatics, Campus E 1.4, 66123, Saarbrücken, Germany

    Bernt Schiele

Rights and permissions

Reprints 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)

Publish with us

Policies and ethics

Search

Navigation