A method is disclosed. Input data indicates a location within a region of a digital image of a stereo image pair. A boundary of the region and a corresponding boundary of a corresponding region of another digital image are defined based on the input data, content of the digital image, and content of the another digital image. The boundary and the corresponding boundary represent boundaries of a visual feature in the digital image and the other digital image. The defining further includes constructing a probability distribution for the digital image and another probability distribution for the other digital image. The probability distribution for the digital image represents a probability that each pixel of a set of pixels of the digital image is within the region. The other probability distribution represents a probability that each pixel of another set of pixels of the another digital image is within the corresponding region.