Patrick Vandewalle

TL;DR: A frequency domain technique to precisely register a set of aliased images, based on their low-frequency, aliasing-free part, and a high-resolution image is then reconstructed using cubic interpolation.

TL;DR: If the experiments are performed on a large data set, the algorithm is compared to the state-of-the-art methods, the code and/or data are well documented and available online, the community will all benefit and make it easier to build upon each other's work.

TL;DR: If the experiments are performed on a large data set, the algorithm is compared to the state-of-the-art methods, the code and/or data are well documented and available online, the community will all benefit and make it easier to build upon each other's work.

TL;DR: It is proved that the solution of the registration and reconstruction problem is generically unique if MN ges L + M - 1, and two subspace-based methods to compute this solution are described.

TL;DR: In this article, a method of encoding a video data signal is proposed, which consists of providing at least a first image (21) of a scene (100) as seen from a first viewpoint, providing rendering information (22) for enabling the generation of at least one rendered image of the scene(100) from a rendering viewpoint, and defining a preferred orientation of the rendering viewpoint relative to the first viewpoint.