In this paper we review several algorithms for image inpainting based on thehypoelliptic diffusion naturally associated with a mathematical model of theprimary visual cortex. In particular, we present one algorithm that does notexploit the information of where the image is corrupted, and others that do it.While the first algorithm is able to reconstruct only images that our visualsystem is still capable of recognize, we show that those of the second typecompletely transcend such limitation providing reconstructions at thestate-of-the-art in image inpainting. This can be interpreted as a validationof the fact that our visual cortex actually encodes the first type ofalgorithm.
展开▼