Color Photometric Stereo Using a Rainbow Light for Non-Lambertian Multicolored Surfaces

This paper presents a novel approach for recovering the shape of non-Lambertian, multicolored objects using two input images. We show that a ring light source with complementary colored lights has the potential to be effectively utilized for this purpose. Under this lighting, the brightness of an object surface varies with respect to different reflections. Therefore, analyzing how brightness is modulated by illumination color gives us distinct cues to recover shape. Moreover, the use of complementary colored illumination enables the color photometric stereo to be applicable to multicolored surfaces. Here, we propose a color correction method based on the addition principle of complementary colors to remove the effect of illumination from the observed color. This allows the inclusion of surfaces with any number of chromaticities. Therefore, our method offers significant advantages over previous methods, which often assume constant object albedo and Lambertian reflectance. To the best of our knowledge, this is the first attempt to employ complementary colors on a ring light source to compute shape while considering both non-Lambertian reflection and spatially varying albedo. To show the efficacy of our method, we present results on synthetic and real world images and compare against photometric stereo methods elsewhere in the literature.