Novel Multi-view Synthesis from a Stereo Image Pair for 3D Display on Mobile Phone

  • Chen-Hao Wei
  • Chen-Kuo Chiang
  • Yu-Wei Sun
  • Mei-Huei Lin
  • Shang-Hong Lai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7729)

Abstract

In this paper we present a novel view synthesis method for mobile platform. A disparity-based view interpolation is proposed to synthesize the virtual view from a left and right image pair. This makes to full use of the available information of both images to give accurate interpolation results and greatly decreases the pixel number in the disoccusion region, thus reducing the errors introduced by the patch-based image inpainting. Two boundary refining schemes considering gradient and color coherence and applying directional filters on boundaries are proposed to improve the synthesized results. Experimental results show that the proposed method is effective and suitable for mobile environment.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2000, pp. 417–424. ACM Press/Addison-Wesley Publishing Co., New York (2000)CrossRefGoogle Scholar
  2. 2.
    Oh, K.J., Yea, S., Ho, Y.S.: Hole filling method using depth based in-painting for view synthesis in free viewpoint television and 3-d video. In: Proceedings of the 27th Conference on Picture Coding Symposium, PCS 2009, pp. 233–236. IEEE Press, Piscataway (2009)Google Scholar
  3. 3.
    Lin, S.J., Cheng, C.M., Lai, S.H.: Spatio-temporally Consistent Multi-view Video Synthesis for Autostereoscopic Displays. In: Muneesawang, P., Wu, F., Kumazawa, I., Roeksabutr, A., Liao, M., Tang, X. (eds.) PCM 2009. LNCS, vol. 5879, pp. 532–542. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  4. 4.
    Criminisi, A., Pérez, P., Toyama, K.: Object removal by exemplar-based inpainting. In: CVPR (2), pp. 721–728 (2003)Google Scholar
  5. 5.
    Shen, J., Jin, X., Zhou, C.: Gradient Based Image Completion by Solving Poisson Equation. In: Ho, Y.-S., Kim, H.-J. (eds.) PCM 2005, Part I. LNCS, vol. 3767, pp. 257–268. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Komodakis, N.: Image completion using global optimization. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 442–452. IEEE Computer Society, Washington, DC (2006)Google Scholar
  7. 7.
    Sun, J., Yuan, L., Jia, J., Shum, H.Y.: Image completion with structure propagation. ACM Trans. Graph. 24, 861–868 (2005)CrossRefGoogle Scholar
  8. 8.
    Ting, H., Chen, S., Liu, J., Tang, X.: Image inpainting by global structure and texture propagation. In: Proceedings of the 15th International Conference on Multimedia, MULTIMEDIA 2007, pp. 517–520. ACM, New York (2007)Google Scholar
  9. 9.
    Xi, M., Wang, L.H., Yang, Q.Q., Li, D.X., Zhang, M.: Multiview virtual image synthesis for auto-stereoscopic display based on two views. In: International Conference on Systems and Informatics (ICSAI), pp. 1966–1970 (2012)Google Scholar
  10. 10.
    Ahn, I., Kim, C.: Depth-based disocclusion filling for virtual view synthesis. In: International Conference on Multimedia Expo (ICME) (2012)Google Scholar
  11. 11.
    Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: CVPR (2007)Google Scholar
  12. 12.
    ISO/IEC JTC1/SC29/WG11: View synthesis software manual, release 3.5. In: MPEG (2009)Google Scholar
  13. 13.
    Fehn, C.: Depth-image-based rendering (dibr), compression, and transmission for a new approach on 3d-tv. In: Proceedings of SPIE, vol. 5291, pp. 93–104 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Chen-Hao Wei
    • 1
  • Chen-Kuo Chiang
    • 1
  • Yu-Wei Sun
    • 1
  • Mei-Huei Lin
    • 1
  • Shang-Hong Lai
    • 1
  1. 1.National Tsing Hua UniversityHsinchuTaiwan, R.O.C.

Personalised recommendations