Texture-aware edit propagation using nonparametric regression

Edit propagation is a class of algorithms that propagates user-specified color adjustments across an image or video. The user-specified adjustments take the form of sparse paint strokes that give examples of the desired alterations. Existing edit propagation (EP) algorithms are based on color similarity, and thus will alter all objects that have a similar color. In this work, we describe an EP algorithm that also considers texture, so that only objects with similar textural properties are edited. Since the method requires a high dimensional feature space, we also consider a random projection approach to reduce the effects of the curse of dimensionality.