Image restoration from multiple copies: A GMM based method

Recovery of original images from degraded and noisy observations is considered an important task in image processing. Recently, a Piece-wise Linear Estimator (PLE) was proposed for image recovery by using Gaussian Mixture Model (GMM) as a prior for image patches. Despite having much lesser computational requirements, this method yields comparable or better results when compared with the widely used sparse representation techniques for image restoration. In many situations, we might have access to multiple degraded copies of the same image, and would like to exploit the correlation among them for better image recovery. In this work, we extend the GMM based method to the multiple observations scenario, where we estimate the original image by utilizing the collective information available from all degraded copies.