TR2006-048

Extensions of H.264/AVC for Multiview Video Compression

    •  Martinian, E., Behrens, A., Xin, J., Vetro, A., Sun, H., "Extensions of H.264/AVC for Multiview Video Compression", IEEE International Conference on Image Processing (ICIP), October 2006, pp. 2981-2984.
      BibTeX TR2006-048 PDF
      • @inproceedings{Martinian2006oct1,
      • author = {Martinian, E. and Behrens, A. and Xin, J. and Vetro, A. and Sun, H.},
      • title = {Extensions of H.264/AVC for Multiview Video Compression},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2006,
      • pages = {2981--2984},
      • month = oct,
      • issn = {1522-4880},
      • url = {https://www.merl.com/publications/TR2006-048}
      • }
  • MERL Contacts:
  • Research Area:

    Digital Video

Abstract:

We consider multiview video compression: the problem of jointly compressing multiple views of a scene recorded by different cameras. To take advantage of the correlation between views, we propose using disparity compensated view prediction and view synthesis and describe how these features can be implemented by extending the H.264/AVC compression standard. Finally, we discuss experimental results on the test sequences from the MPEG Call for Proposals on multiview video.

 

  • Related News & Events

    •  NEWS    ICIP 2006: 3 publications by Oncel Tuzel, Anthony Vetro, Huifang Sun and others
      Date: October 8, 2006
      Where: IEEE International Conference on Image Processing (ICIP)
      MERL Contacts: Anthony Vetro; Huifang Sun
      Brief
      • The papers "Extensions of H.264/AVC for Multiview Video Compression" by Martinian, E., Behrens, A., Xin, J., Vetro, A. and Sun, H., "Fast Construction of Covariance Matrices for Arbitrary Size Image Windows" by Porikli, F. and Tuzel, O. and "A Cascading Framework of Contour Motion and Deformation Estimation for Non-Rigid Object Tracking" by Shao, J., Porikli, F. and Chellappa, R. were presented at the IEEE International Conference on Image Processing (ICIP).
    •