A system for performing background and floor replacement in full-length subject images is described. A set of three or more images of a subject can be captured under different illumination conditions. For example, at least one of the images is captured while a foot portion of the subject and surrounding floor, including a floor mat on which the subject is positioned, are illuminated by a floor lighting device. The floor mat has a Lambertian surface to reflect light in a particular manner such that a maximum contrast between the floor and the subject is captured in the image. Varying contrast between the background, floor, and subject among the images of the set can be leveraged by an image processing system to generate a background mask and a floor mask that are combined and seamlessly transitioned to yield a compiled mask for use in background and floor replacement.