Gq. Wei et G. Hirzinger, PARAMETRIC SHAPE-FROM-SHADING BY RADIAL BASIS FUNCTIONS, IEEE transactions on pattern analysis and machine intelligence, 19(4), 1997, pp. 353-365
In this paper, we present a new method of shape from shading by using
radial basis functions to parameterize the object depth. The radial ba
sis functions are deformed by adjusting their centers, widths, and wei
ghts such that the intensity errors are minimized. The initial centers
and widths are arranged hierarchically to speed up convergence and to
stabilize the solution. Although the smoothness constraint is used, i
i can be eventually dropped out without causing instabilities in the s
olution. An important feature of our parametric shape-from-shading met
hod is that it offers a unified framework for integration of multiple
sensory information. We show that knowledge about surface depth and/or
surface normals anywhere in the image can be easily incorporated into
the shape from shading process. It is further demonstrated that even
qualitative knowledge can be used in shape from shading to improve 3D
reconstruction. Experimental comparisons of our method with several ex
isting ones are made by using both synthetic and real images. Results
show that our solution is more accurate than the others.