Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach. (arXiv:2204.10090v3 [eess.IV] UPDATED)

Collecting paired training data is difficult in practice, but the unpaired
samples broadly exist. Current approaches aim at generating synthesized
training data from unpaired samples by exploring the relationship between the
corrupted and clean data. This work proposes LUD-VAE, a deep generative method
to learn the joint probability density function from data sampled from marginal
distributions. Our approach is based on a carefully designed probabilistic
graphical model in which the clean and corrupted data domains are conditionally
independent. Using variational …

arxiv bayes data image