A Bayesian framework for reconstructing missing data in colour image sequences

This paper presents a Bayesian framework for reconstructing missing regions of a colour image sequence. Because the three colour channels are not independent a multichannel median (vector median) image model is chosen. Since the model extends through time to previous and following frames it incorporates motion estimation to compensate for the effects of motion in the original scene. The paper discusses methods for detecting the missing data which exploit the temporally uncorrelated nature of typical degradation. A Markov Chain Monte Carlo (MCMC) Gibb's Sampling scheme is adopted for drawing samples for the missing data. The method draws these from the full posterior distributions for the missing data in each of the YUV colour channels The nature of the model means that the multivariate probability distributions for the missing data are difficult to sample from. The paper shows how this can be overcome with a numerical approach to the sampling. The efficiency of this approach relies on the fact that there are only a small and finite number of values that the data can take. The noise process for each channel is modelled with a zero-mean Laplacian distribution. It is shown that samples for the variances can be drawn from the Gamma distribution.