Wyner-ziv Coding of Stereo Images with Unsupervised Learning of Disparity

  title={Wyner-ziv Coding of Stereo Images with Unsupervised Learning of Disparity},
  author={David P. Varodayan and Yao-Chung Lin and Aditya Mavlankar and Markus Flierl and Bernd Girod},
Wyner-Ziv coding can exploit the similarity of stereo images without communication among the cameras. For good compression performance, the disparity among the images should be known at the decoder. Since the Wyner-Ziv encoder has access only to one image, the disparity must be inferred from the compressed bitstream. We develop an Expectation Maximization algorithm to perform unsupervised learning of disparity at the decoder. Our experiments with natural stereo images show that the unsupervised… CONTINUE READING
Highly Cited
This paper has 45 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 24 extracted citations


Publications referenced by this paper.
Showing 1-10 of 13 references

Digital compression and coding of continuous-tone still images

  • ISO/IEC 10918-1 — ITU-T Recommendation T.81 (JPEG…
  • 1992
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…