Modeling Surface from a Single Grayscale Image

In this paper we show how a system for performing automatic surface model acquisition from a single grayscale image can be designed in two steps. Firstly, surface normals are parallelly and gradually adjusted by a procedure which includes three constraints: smooth constraint ensures the recovered normals are smooth and integrable, intensity gradient constraint ensures the recovered normals are consistent with the image gradient field and intensity constraint guarantees the recovered intensity is equal to the input image. Secondly, the surface is recovered from needle map using a two-dimension cellular automata system. The experiment results demonstrate this approach is practicable.