We present a robust and efficient approach for zoom-based super-resolution (SR) reconstruction problems. We employ the total variation (TV) of the desired image priori in the maximum a-posteriori estimation. An efficient algorithm based on iterative methods and preconditioning techniques is employed to solve the resulting variational problem. To suit the proposed algorithm for realistic imaging situations, a registration method is presented to simultaneously solve the zooming factors, image center shifts, and photometric parameters. Experimental results show that the proposed TV-based algorithm performs quite well in terms of both quantitative measurements and visual evaluation. We also demonstrate that the proposed algorithm is robust for SR image inpainting, where some pixels are missed in the SR reconstruction model.
In this paper, we present a technique for generating a high-
resolution image from a blurred image sequence. The image sequence
consists of decimated, blurred and noisy versions of the high-
resolution image. The high-resolution image is modeled as a Markov
random field, and a maximum a posteriori estimation technique is used
for image restoration. A fast algorithm based on Fast Fourier
Transforms (FFTs) is derived to solve the resulting linear system.
Numerical examples are given to illustrate the effectiveness of the