Image Inpainting With Data-Adaptive Sparsity
Ivan V. Bajić · 2014
Ima ge inpainting finds numerous applications in object removal, error concealment, view synthesis, and so on.Among the existing methods, exemplar-based inpainting has been shown to achieve superior performance when filling in large areas.This paper presents a review of inpainting based on sparse representations, as a generalization of conventional exemplar-based inpainting.The importance of data-driven adaptation of the sparsity level according to the image content is emphasized.Experimental results show that incorporating data-adaptive sparsity leads to improvement in both subjective and objective inpainting performance compared to well-known exemplar-based inpainting.