Bayesian Scheme for Interactive Colorization, Recolorization and Image/Video Editing
Oscar Dalmau, Mariano Rivera, Teresa E. Alarcón, Colonia Valenciana · 2010
We propose a general image and video editing method based on a Bayesian segmentation framework. In the first stage, classes are established from scribbles made by a useron the image. These scribbles can be considered as a multimap (multilabel map) that defines the boundary condit ions of a probability measure field to be computed for each pixel. In the second stage, the global minima of a pos itive definite quadratic cost function with linear constraints, is calculated to find the probability measure field. The components of such a probability measure field express the degree of each pixel belonging to spatially smoo th classes. Finally, the computed probabilities (memberships) are used for defining the weights of a linear combin ation of user provided colors or effects associated to each class. The proposed method allows the application ofdifferent operators, selected interactively by the user, over part or the whole image without needing to recompu te the memberships. We present applications to colorization, recolorization, editing and photomontage t asks.