Existing shape from shading algorithms are not robust enough to work reliably with real images. We present a new paradigm for shape from shading based upon a scale space surface representation. Using this representation, the shape from shading problem becomes one of forming a surface from Gaussian basis functions in such a way that the shading in the original image is explained. The algorithm is extremely robust, producing convincing results even when there is considerable noise present. In its current form, the algorithm requires the reflectance function to be approximately circularly symmetric. We show results for synthetic images, both with and without added noise. and for real scanning electron microscope images. © 1994.