Wyner-ziv coding of stereo images with unsupervised learning of disparity

Wyner-Ziv coding can exploit the similarity of stereo images without communication among the cameras. For good com-pression 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 Max-imization algorithm to perform unsupervised learning of dis-parity at the decoder. Our experiments with natural stereo im-ages show that the unsupervised disparity learning algorithm outperforms a system which does no disparity compensation. It is also superior to conventional compression using JPEG. 1