A convex optimization approach for image resolution enhancement from compressed representations

Quality of experience in future home devices is foreseen to drastically increase, with the increase in image resolution. Displays with a horizontal resolution of 4K pixels are already appearing, and 8K Super-HiVision has already been demonstrated. Currently, only spatial upsampling of conventional HD format is performed to match the resolution of such displays. In this paper, we propose a novel method for high-quality up-conversion of legacy visual content in order to fit the screen resolution. More precisely, by assuming that we have various versions of the same image at standard resolution, encoded with different parameters, we try to reconstruct the high resolution image with higher quality than a simple interpolation. To this end, we adopt a variational formulation of the problem and construct a convex constrained criterion that incorporates both a fidelity term (linked to the acquisition process) and some a priori information. A recent primal-dual proximal algorithm is used to solve the associated minimization problem and simulation results show the good performance and behavior of the proposed approach.