Analysing the optical flow of photometric-stereo images

The shading information in two or more images of a surface, obtained under different illuminations from a single camera, can be used for shape estimation in the process known as photometric stereo (PS). From the observation of the fact that pairs of photometric-stereo images viewed under a stereoscope produce an impression of depth which can be almost as striking as that produced by stereoscopic pairs, we have been led to the study of photometric stereo as a geometric image matching process. We have analysed the possibility of extracting shape information from the optical flow which results from the change of illumination in PS images. Two main results have arisen from our analysis. We have found that, (i) under quite general conditions, the photometric-stereo optical flow (PS flow) can be employed for the estimation of surface curvature; and (ii) under the assumption that a linear approximation to the reflectance map is appropriate, estimates of the relative-depth function can also be obtained from such flow. These results are discussed