Multiframe image restoration in the presence of noisy blur kernel

We wish to recover an original image u from several blurry-noisy versions f_k, called frames. We assume a more severe degradation model, in which the image u has been blurred by a noisy (stochastic) point spread function. We consider the problem of restoring the degraded image in a variational framework. Since the recovery of u from one single frame f is a highly ill-posed problem, we formulate two minimization problems based on the multiframe approach proposed for image super-resolution by Marquina-Osher [2008]. Several experimental results for image restoration are shown, illustrating that the proposed models give visually satisfactory results.