On the editing of images: Selecting, cutting and filling-in

This paper is two-fold. On the one hand, we present a system using qualitative spatial reasoning to help a user choose parts of an image that form interesting objects. The system then allows the user to cut these parts as if unwanted in the original image. On the other hand, we propose a modification of existing texture synthesis methods to create texture in the holes left by the cutting of previously selected areas of the image. This texture synthesis is constrained so that it creates boundaries between regions that are similar to existing ones and fills-in the created regions, yet producing random enough textures so that the new image looks realistic. The context of this work is post-production special effects in cinema or image manipulation where one often wants to remove parts of an image, e.g. when they correspond to props needed for the filming or objects inadvertently included in the shot.