Skip to main content
SpringerLink
Log in

Unsupervised Visual Hull Reconstruction of a Dense Dataset

  • Conference paper
  • First Online:
Computer Vision, Imaging and Computer Graphics - Theory and Applications (VISIGRAPP 2014)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 550))

  • 611 Accesses

Abstract

In this paper a method for the reconstruction of an objects Visual Hull (VH) is presented. An image sequence of a moving object under different lighting condition is captured and analyzed. In this analysis, information from multiple domains (space, time and lighting) is merged based on a MRF framework. The advantage of the proposed method is that it allows to obtain an approximation of an object 3D model without any assumption on object appearance or geometry. Real-data experiments show that the proposed approach allows for robust VH reconstruction of a variety of challenging objects such as a transparent wine glass or a light bulb.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

References

  1. Snow, D., Viola, P., Zabih, R.: Exact voxel occupancy with graph cuts. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) vol. 1, p. 1345 (2000)

    Google Scholar 

  2. Matusik, W., Pfister, H., Ngan, A., Beardsley, P., Ziegler, R., McMillan, L.: Image-based 3d photography using opacity hulls. ACM Trans. Graph. 21, 427–437 (2002)

    Article  Google Scholar 

  3. Baumgart, B.G.: Geometric modeling for computer vision. Ph.D. thesis, Stanford, CA, USA (1974)

    Google Scholar 

  4. Smith, A.R., Blinn, J.F.: Blue screen matting. In: ACM International Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), pp. 259–268 (1996)

    Google Scholar 

  5. Jagers, M., Birkbeck, N., Cobzas, D.: A three-tier hierarchical model for capturing and rendering of 3d geometry and appearance from 2d images. In: International Symposium on 3-D Data Processing, Visualization, and Transmission (3DPVT) (2008)

    Google Scholar 

  6. Zongker, D.E., Werner, D.M., Curless, B., Salesin, D.H.: Environment matting and compositing. In: ACM International Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), pp. 205–214 (1999)

    Google Scholar 

  7. Piccardi, M.: Background subtraction techniques: a review. In: International Conference on Systems, Man and Cybernetics (SMC), pp. 3099–3104 (2004)

    Google Scholar 

  8. Radke, R.J., Andra, S., Al-Kofahi, O., Roysam, B.: Image change detection algorithms: a systematic survey. IEEE Trans. Image Process. 14, 294–307 (2005)

    Article  MathSciNet  Google Scholar 

  9. Parks, D.H., Fels, S.S.: Evaluation of background subtraction algorithms with post-processing. In: International Conference on Advanced Video and Signal Based Surveillance, pp. 192–199 (2008)

    Google Scholar 

  10. Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: Eighth IEEE International Conference on Computer Vision (ICCV), vol. 1, pp. 105–112 (2001)

    Google Scholar 

  11. Campbell, N., Vogiatzis, G., Hernndez, C., Cipolla, R.: Automatic 3d object segmentation in multiple views using volumetric graph-cuts. In: British Machine Vision Conference, vol. 1, pp. 530–539 (2007)

    Google Scholar 

  12. Lee, W., Woo, W., Boyer, E.: Identifying foreground from multiple images. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part II. LNCS, vol. 4844, pp. 580–589. Springer, Heidelberg (2007)

    Chapter  Google Scholar 

  13. Wu, C., Liu, Y., Ji, X., Dai, Q.: Multi-view reconstruction under varying illumination conditions. In: Proceedings of the IEEE International Conference on Multimedia and Expo, pp. 930–933 (2009)

    Google Scholar 

  14. Rother, C., Kolmogorov, V., Blake, A.: “Grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Vision and Systems Laboratory, Laval University, Quebec, QC, Canada

    Maxim Mikhnevich & Denis Laurendeau

Authors
  1. Maxim Mikhnevich
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Denis Laurendeau
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Maxim Mikhnevich .

Editor information

Editors and Affiliations

  1. Dip. di Matematica e Informatica, Università di Catania, Catania, Catania, Italy

    Sebastiano Battiato

  2. Inria/ZIRST, Saint Ismier, France

    Sabine Coquillart

  3. INRIA-Rennes/MimeTIC Tean, Rennes cedex, France

    Julien Pettré

  4. Swansea University, Swansea, UK

    Robert S. Laramee

  5. Computer Science, Linnaeus University, Växjö, Sweden

    Andreas Kerren

  6. do IPS, Escola Superior de Tecnologia, Setúbal, Portugal

    José Braz

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Mikhnevich, M., Laurendeau, D. (2015). Unsupervised Visual Hull Reconstruction of a Dense Dataset. In: Battiato, S., Coquillart, S., Pettré, J., Laramee, R., Kerren, A., Braz, J. (eds) Computer Vision, Imaging and Computer Graphics - Theory and Applications. VISIGRAPP 2014. Communications in Computer and Information Science, vol 550. Springer, Cham. https://doi.org/10.1007/978-3-319-25117-2_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-25117-2_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-25116-5

  • Online ISBN: 978-3-319-25117-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation