TR2014-091

Depth-Assisted Stereo Video Enhancement Using Graph-Based Approaches


    •  Tian, D., Mansour, H., Vetro, A., Wang, Y., Ortega, A., "Depth-assisted Stereo Video Enhancement Using Graph-based Approaches", IEEE International Conference on Image Processing (ICIP), DOI: 10.1109/​ICIP.2014.7025013, October 2014, pp. 71-75.
      BibTeX TR2014-091 PDF
      • @inproceedings{Tian2014oct,
      • author = {Tian, D. and Mansour, H. and Vetro, A. and Wang, Y. and Ortega, A.},
      • title = {Depth-assisted Stereo Video Enhancement Using Graph-based Approaches},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2014,
      • pages = {71--75},
      • month = oct,
      • doi = {10.1109/ICIP.2014.7025013},
      • isbn = {978-1-4799-5750-7},
      • url = {https://www.merl.com/publications/TR2014-091}
      • }
  • MERL Contacts:
  • Research Area:

    Digital Video

Abstract:

In stereo video applications, the quality of the two views may vary based on different camera capturing conditions and setup, compression/transmission, and sensor noise. Although some studies show that the perceived video quality may not be significantly affected by the lower quality view, maintaining a similar video quality is still desired in order to prevent eye strain during extended viewing sessions. In this paper, we study a graph-based approach to enhance the lower quality views by referring to the high quality view in addition to an accompanying depth map. We construct a graphical signal model with joint bilateral edge weights and show that graph-based joint bilateral filtering can better suppress several types of noises, e.g., Gaussian, motion as well as quantization noise.