Boundary conditions for Shape from Shading

TL;DR

This paper examines the limitations of using singular points in shape from shading to resolve local ambiguities and suggests that additional information is necessary for accurate 3D reconstruction.

Contribution

It demonstrates that relying solely on singular points is insufficient and highlights the need for supplementary data to improve shape from shading methods.

Findings

Singular points alone do not fully resolve local ambiguity.

Additional information is required for accurate 3D shape reconstruction.

The study emphasizes the limitations of current graph-based methods.

Abstract

The Shape From Shading is one of a computer vision field. It studies the 3D reconstruction of an object from a single grayscale image. The difficulty of this field can be expressed in the local ambiguity (convex / concave). J.Shi and Q.Zhu have proposed a method (Global View) to solve the local ambiguity. This method based on the graph theory and the relationship between the singular points. In this work we will show that the use of singular points is not sufficient and requires further information on the object to resolve this ambiguity.