A method includes determining, from a first image, a first region comprising teeth, wherein the first region comprises a first set of pixel locations. A first parametric function is generated based on intensities at the first set of pixel locations. Image data comprising new contours of the mouth is received, wherein one or more of the teeth have a different position in the image data than in the first image. A second region comprising the teeth is determined from the image data, wherein the second region comprises a second set of pixel locations for the teeth. A new image is then generated based on the image data and the first parametric function, wherein a shape of the teeth is based on the image data and a color of the teeth is based on applying the first parametric function to the second set of pixel locations for the teeth.
