3D Conversion of 2D H.264 Video 


Vol. 31,  No. 12, pp. 1208-1215, Dec.  2006


PDF
  Abstract

In this paper, we propose an algorithm that creates three-dimensional (3D) stereoscopic video from two-dimensional (2D) video encoded by H.264 instead of using the conventional stereo-camera process. Motion information of each frame can be obtained by the given motion vectors in most of videos encoded by MPEG standards. Especially, we have accurate motion vectors for H.264 streams because of the availability of a variety of block sizes. 2D/3D video conversion algorithm proposed in this paper can create the left and right images that correspond to the original image by using cut detection method, delay factors, motion types, and image types. We usually have consistent motion type and direction in a given cut because each frame in the same cut has high correlation. We show the improved performance of the proposed algorithm through experimental results.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

H. Hong, Y. Baek, S. H. Lee, D. Kim, J. Yoo, "3D Conversion of 2D H.264 Video," The Journal of Korean Institute of Communications and Information Sciences, vol. 31, no. 12, pp. 1208-1215, 2006. DOI: .

[ACM Style]

Ho-ki Hong, Yun-ki Baek, Seung Hyun Lee, Dong-Wook Kim, and Ji-sang Yoo. 2006. 3D Conversion of 2D H.264 Video. The Journal of Korean Institute of Communications and Information Sciences, 31, 12, (2006), 1208-1215. DOI: .

[KICS Style]

Ho-ki Hong, Yun-ki Baek, Seung Hyun Lee, Dong-Wook Kim, Ji-sang Yoo, "3D Conversion of 2D H.264 Video," The Journal of Korean Institute of Communications and Information Sciences, vol. 31, no. 12, pp. 1208-1215, 12. 2006.