In this paper an innovative algorithm to reproduce non-uniform, photorealistic, gray-scale images on large surfaces, using an ordinary industrial spray-painting robot is proposed. The algorithm splits the process into a set of iterative steps with decreasing spray-gun stroke diameters. Thus, it can efficiently build up the image starting with large strokes to paint the larger details of the image. Then, with increasingly smaller strokes, it can paint the rest of the smaller details. The target image is segmented and a tool-path is computed. A set of critical points in the image is then chosen to avoid oversaturation and used to implement an algorithm to calculate spray-gun operational speed at each path point. Eventually, such conditions lead to a linear system which is solved using an ordinary least squares method. Depending on the image to reproduce, this methodology promises to be far more efficient than painting processes where the image is built entirely at the smallest detail level. For this reason, it would be particularly suitable for large building façade decoration, for example.
