High-speed texture-preserving digital image inpainting

Automatic image in-painting is a process that attempts to automatically restore flaws in digitized images. The objective is to automatically fill in missing data simulating results achieved manually by professional painting restorators. Inpainting can be employed to remove objects as well as text, but more importantly to repair imperfections in images and scanned photographs. In this paper we present a novel inpainting algorithm which improves upon previous work by significantly reducing the time required to inpaint an image, yet providing improved visual results as well. Furthermore, our algorithm works well on larger restoration areas by estimating a functional view of texture and therefore maintains the texture in the in-painted regions.