3D VISUALIZATION OF SINGLE IMAGES USING PATCH LEVEL DEPTH

Shahrouz Yousefi, Farid Abedan Kondori, Haibo Li

Abstract

In this paper we consider the task of 3D photo visualization using a single monocular image. The main idea is to use single photos taken by capturing devices such as ordinary cameras, mobile phones, tablet PCs etc. and visualize them in 3D on normal displays. Supervised learning approach is hired to retrieve depth information from single images. This algorithm is based on the hierarchical multi-scale Markov Random Field (MRF) which models the depth based on the multi-scale global and local features and relation between them in a monocular image. Consequently, the estimated depth image is used to allocate the specified depth parameters for each pixel in the 3D map. Accordingly, the multi-level depth adjustments and coding for color anaglyphs is performed. Our system receives a single 2D image as input and provides a anaglyph coded 3D image in output. Depending on the coding technology the special low-cost anaglyph glasses for viewers will be used.

References

  1. Chaudhuri, S., R. A. (1999). Depth from defocus: A real aperture imaging approach. In ISBN: 0387986359. Springer.
  2. Das, S. and Ahuja, N. (1995). Performance analysis of stereo, vergence, and focus as depth cues for active vision. In PAMI.
  3. Dubois, E. (2001). A projection method to generate anaglyph stereo images. In Proc. IEEE Int. Conf. Acoustics Speech Signal Processing. IEEE Computer Society Press.
  4. Forsyth, D. and Ponce, J. (2003). In Computer Vision: A Modern Approach. Prentice Hall.
  5. Hartley, R. and Zisserman, A. (2003). In Multiple View Geometry in Computer Vision.
  6. Holliman, N. (2004). Mapping perceived depth to regions of interest in stereoscopic images. In Proc. SPIE Vol. 5291, Stereoscopic Displays and Virtual Reality Systems XI.
  7. Jones, G., Lee, D., Holliman, N., and Ezra, D. (2001). Controlling perceived depth in stereoscopic images. In Stereoscopic Displays and Virtual Reality Systems VIII. 200-1.
  8. Lindeberg, T. and Garding, J. (1993). Shape from texture from a multi-scale perspective. In Computer Vision, 1993. Proceedings., Fourth International Conference on.
  9. Maki, A., Watanabe, M., and Wiles, C. (2002). Geotensity: Combining motion and lighting for 3d surface reconstruction. In IJCV. Springer.
  10. Malik, J. and Perona, P. (1990). Preattentive texture discrimination with early vision mechanisms. In Journal of the Optical Society of America.
  11. Malik, J. and Rosenholtz, R. (1997). Computing local surface orientation and shape from texture forcurved surfaces. In IJCV. Kluwer Academic Publishers.
  12. Mcallister, D., Zhou, Y., and Sullivan, S. (2010). Methods for computing color anaglyphs.
  13. Michels, J., Saxena, A., and Y. Ng, A. (2005). High speed obstacle avoidance using monocular vision and reinforcement learning. In In ICML.
  14. Nagai, T., Naruse, T., Ikehara, M., and Kurematsu, A. (2002). Hmm-based surface reconstruction from single images. In Image Processing. 2002. Proceedings. 2002 International Conference on.
  15. Quartulli, M. and Datcu, M. (2001). Bayesian model based city reconstruction from high resolution isar data. In IEEE/ISPRS joint workshop remote sensing and data fusion over urban areas.
  16. Saxena, A., Chung, S., and Ng, A. (2005). Learning depth from single monocular images. In NIPS 18. MIT Press.
  17. Saxena, A., Sun, M., and Ng, A. (2007). Learning 3-d scene structure from a single still image. In ICCV workshop on 3D Representation for Recognition.
  18. Saxena, A., Sun, M., and Ng, A. (2008). Make3d: Learning 3d scene structure from a single still image. In Pattern Analysis and Machine Intelligence, IEEE Transactions on.
  19. Scharstein, D. and Szeliski, R. (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. In IJCV.
  20. Sinha, P., Blthoff, I., and Blthoff, H. (1998). Top-down influences on stereoscopic depth-perception. In Nature Neuroscience, 1:254257.
  21. Tran, V. (2005). New methods for rendering of anaglyph stereoscopic images on crt displays and photo-quality ink-jet printers. In Ottawa-Carleton Institute for Electrical and Computer Engineering.
  22. Wimmer, P. (2005). Anaglyph methods comparison. In http://www.3dtv.at/Knowhow/.
  23. Wu, B., Ooi, T., and He, Z. (2004). Perceiving distance accurately by a directional process of integrating ground information. In Letters to Nature, 428:7377.
  24. Zhang, R., Tsai, P., Cryer, J., and Shah, M. (1999). Shapefrom-shading: a survey. In Pattern Analysis and Machine Intelligence, IEEE Transactions on.
Download


Paper Citation


in Harvard Style

Yousefi S., Abedan Kondori F. and Li H. (2011). 3D VISUALIZATION OF SINGLE IMAGES USING PATCH LEVEL DEPTH . In Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2011) ISBN 978-989-8425-72-0, pages 61-66. DOI: 10.5220/0003511800610066


in Bibtex Style

@conference{sigmap11,
author={Shahrouz Yousefi and Farid Abedan Kondori and Haibo Li},
title={3D VISUALIZATION OF SINGLE IMAGES USING PATCH LEVEL DEPTH},
booktitle={Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2011)},
year={2011},
pages={61-66},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003511800610066},
isbn={978-989-8425-72-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Signal Processing and Multimedia Applications - Volume 1: SIGMAP, (ICETE 2011)
TI - 3D VISUALIZATION OF SINGLE IMAGES USING PATCH LEVEL DEPTH
SN - 978-989-8425-72-0
AU - Yousefi S.
AU - Abedan Kondori F.
AU - Li H.
PY - 2011
SP - 61
EP - 66
DO - 10.5220/0003511800610066