A Parametric Method of Shape-from-Shading and Experimental Comparisons

In this paper, we present a new method of shape from shading by using radial basis functions to parameterize the object depth. The radial basis functions are deformed by adjusting their centers, widths, and weights such that the intensity errors are minimized. An important feature of our parametric shape-from-shading method is that it offers an unified framework for integration of multiple sensory information. We show that both quantitative and qualitative knowledge about surface depth and/or surface normals anywhere in the image can be easily incorporated into the shape from shading process. Experimental comparisons of our method with several existing ones are made by using both synthetic and real images.