Skip to main content
SpringerLink
Log in

Automatic generation of 3D outdoor and indoor building scenes from a single image

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In this paper, a novel approach for creating 3D models of building scenes is presented. The proposed method is fully automated and fast, and accurately reconstructs both outdoor images of a building and indoor scenes, with perspective cues in real-time, using only one image. It combines the extracted line segments to identify the vanishing points of the image, the orientation, the different planes that are depicted in the image and concludes whether the image depicts indoor or outdoor scenes. In addition, the proposed method efficiently eliminates the perspective distortion and produces an accurate 3D model of the scene without any intervention from the user. The main innovation of the method is that it uses only one image for the 3D reconstruction, while other state-of-the-art methods rely on the processing of multiple images. A website and a database of 100 images were created to prove the efficiency of the proposed method in terms of time needed for the 3D reconstruction, its automation and 3D model accuracy and can be used by anyone so as to easily produce user-generated 3D content: http://3d-test.iti.gr:8080/3d-test/3D_recon/

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Aguilera DG, Gómez Lahoz J, Finat Codes J (2005) A new method for vanishing points detection in 3D reconstruction from a single view. International Workshop on 3D Virtual Reconstruction and Visualization of Complex Architectures (3D-ARCH ’05), Venice

  2. Canny J (1986) A computational approach to edge detection. IEEE Trans. Pattern Analysis and Machine Intelligence

  3. Criminisi IR, Zisserman A (2000) Single view metrology. Int. J. Computer Vision, 40(2):pp 123–148. http://portal.acm.org/citation.cfm?id=365888

    Google Scholar 

  4. Debevec PE (1996) Modeling and rendering architecture from photographs. PhD thesis, University of California at Berkeley, Computer Science Division, Berkeley CA

  5. Delage, HL, Ng AY (2006) A dynamic Bayesian network model for autonomous 3D reconstruction from a single indoor image. Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, 2: pp 2418-2428. http://www.stanford.edu/~hllee/cvpr06_3dReconIndoorScene.pdf

  6. Google Sketch Up. http://sketchup.google.com/

  7. Hartley R, Zisserman A (2003) Multiple view geometry in computer vision. Cambridge University Press, pp 47–57

  8. Hoiem D (2005) Alexei A. Efros and Martial Hebert. Automatic Photo Pop-up. ACM SIGGRAPH

  9. Hoiem D, Efors A, Hebert M (2005) Geometric context from a single image. In Proceedings of IEEE Conference Computer Vision and Pattern Recognition. http://www.cs.uiuc.edu/homes/dhoiem/publications/Hoiem_Geometric.pdf

  10. Horry Y, Anjyo K-I, Arai K (1997) Tour into the picture: using a spidery mesh interface to make animation from a single image. Proceedings of the 24th annual conference on Computer graphics and interactive techniques, pp 225-232. [doi:10.1145/258734.258854]

  11. Huang J, Cowan B (2009) Simple 3D Reconstruction of Single Indoor Image with Perspective Cues. crv, pp.140-147. Canadian Conference on Computer and Robot Vision. http://www.computer.org/portal/web/csdl, doi:10.1109/CRV.2009.33

  12. Illingworth J, Kittler J (1988) A survey of the hough transform. Comput Vis Graph Image Process 44(1):87–116

    Article  Google Scholar 

  13. Lee DC, Hebert M, Kanade T (2009) Geometric reasoning for single image structure recovery. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June. www.cs.cmu.edu/~dclee/pub/cvpr09lee.pdf

  14. Liebowitz D (1999) Antonio Criminisi, and Andrew Zisserman. 1999. Creating Architectural Models from Images. In Proc. EuroGraphics, vol 18. http://www.robots.ox.ac.uk/~vgg/publications/papers/liebowitz99.pdf.

  15. Liebowitz D (2001) Camera calibration and reconstruction of geometry from images. Merton College Robotics Research Group Department of Engineering Science University of Oxford Trinity Term 2001. http://www.robots.ox.ac.uk/~vgg/publications/papers/liebowitz01.pdf

  16. Rother (2000) A new approach for vanishing point detection in architectural environments. In BMVC, pages 382-391. www.bmva.org/bmvc/2000/papers/p39.pdf

  17. Rother C (2002) A new approach to vanishing point detection in architectural environments. Image Vis Comput 20(9–10):647–655

    Article  Google Scholar 

  18. Saxena A, Chung SH, AY Ng (2005) Learning depth from single monocular images. In Neural Information Processing Systems (NIPS). http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.8799

  19. Saxena A, Sun M, Ng A (2007) Learning 3-D Scene Structure from a Single Still Image. In: Proc. of ICCV workshop on 3D representation for Recognition

  20. Saxena A, Chung SH, Ng AY (2007) 3-d depth reconstruction from a single still image. IJCV

  21. Van den Heuvel FA (1998) Vanishing point detection for architectural Photogrammetry. Int Arch Photogram Rem Sens 32(5):652–659

    Google Scholar 

Download references

Acknowledgments

This work was supported by the EU FP7 project 3DLife Network of Excellence project, ICT-247688.

Author information

Authors and Affiliations

  1. Information Processing Laboratory, Department of Electrical and Computer, Engineering Aristotle University of Thessaloniki, GR54124, Thessaloniki, Greece

    Georgios Vouzounaras & Michael G. Strintzis

  2. Informatics and Telematics Institute, Centre for Research and Technology Hellas, GR57001, Thessaloniki, Greece

    Petros Daras & Michael G. Strintzis

Authors
  1. Georgios Vouzounaras
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Petros Daras
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Michael G. Strintzis
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Petros Daras.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Vouzounaras, G., Daras, P. & Strintzis, M.G. Automatic generation of 3D outdoor and indoor building scenes from a single image. Multimed Tools Appl 70, 361–378 (2014). https://doi.org/10.1007/s11042-011-0823-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-011-0823-0

Keywords

Search

Navigation