Exemplar-based interpolation of sparsely sampled images

Presentation of the paper "Exemplar-based interpolation of sparsely sampled images", Facciolo, Arias, Caselles, and Sapiro, EMMCVPR, 2009.

Presented 2009-08-27, at EMMCVPR'09 Conference, Bonn, Germany.

A nonlocal variational formulation for interpolating a sparsely sampled image is introduced in this paper. The proposed variational for- mulation, 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 inpaint- ing 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.