Abstract

This paper introduces a new examplar-based inpainting framework. A coarse version of the input image is first inpainted by a non-parametric patch sampling. Compared to existing approaches, some improvements have been done (e.g. filling order computation, combina- tion of K nearest neighbours). The inpainted of a coarse version of the input image allows to reduce the computational complexity, to be less sensitive to noise and to work with the dominant orientations of im- age structures. From the low-resolution inpainted image, a single-image super-resolution is applied to recover the details of missing areas. Exper- imental results on natural images and texture synthesis demonstrate the effectiveness of the proposed method.