Exemplar-Based Interpolation of Sparsely Sampled Images

摘要

A nonlocal variational formulation for interpolating a sparsely sampled image is introduced in this paper. The proposed variational formulation, originally motivated by image inpainting problems, encourages the transfer of information between similar image patches, following the paradigm of exemplar-based methods. Contrary to the classical inpainting problem, no complete patches are available from the sparse image samples, and the patch similarity criterion has to be redefined as here proposed. Initial experimental results with the proposed framework, at very low sampling densities, are very encouraging. We also explore some departures from the variational setting, showing a remarkable ability to recover textures at low sampling densities.