Variational Bayesian super-resolution based on composite prior modeling

This paper proposes adaptively combining the known total variation model and more recent Frobenius norm regularization for multi-frame super-resolution (SR). In contrast to existing literature, both composite prior modeling and variational optimization are achieved in the Bayesian framework by utilizing the Kullback-Leibler divergence, and the parameters related to the composite prior and noise statistics are determined adaptively and automatically, resulting in a spatially adaptive SR reconstruction method. Experimental results show that the new method can produce a high-resolution image with higher signal-to-noise ratio and better visual perception.