Abstract Wyner-Ziv Coding of Video with Unsupervised Motion Vector Learning

Distributed source coding theory has long promised a new method of encoding video that is much lower in complexity than conventional methods. In the distributed framework, the decoder is tasked with exploiting the redundancy of the video signal. Among the difficulties in realizing a practical codec has been the problem of motion estimation at the decoder. In this paper, we propose a mechanism for unsupervised learning of forward motion vectors during the decoding of a frame with reference to its previous reconstructed frame. The mechanism, described for both pixel-domain and transform-domain coding, is an instance of the Expectation Maximization algorithm. Our experiments indicate that a video codec based on unsupervised motion learning outperforms a codec with zero motion compensation by up to 1.5 dB. It performs within about 0.5 dB of a codec that knows the motion vectors through an oracle. Keywords: Wyner-Ziv video coding, Expectation Maximization 1