Incorporating illumination constraints in deformable models
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 322-329
- https://doi.org/10.1109/cvpr.1998.698626
Abstract
We present a method for the integration of illumination constraints within a deformable model framework. These constraints are incorporated as nonlinear holonomic constraints in the Lagrange equations of motion governing the deformation of the model. For improved numerical performance we employ the Baumgarte stabilization method. Our methodology is general and can be used for a broad range of illumination constraints. This approach avoids commonly used approximations in shape from shading, such as linearization, and the use of partial differential equations, which require initial boundary conditions. Furthermore, global and local parameterizations of the deformable models allow an improved estimation of shape from shading. We demonstrate this improvement over previously used approaches through a series of experiments on standardized sets of real and synthetic data.Keywords
This publication has 22 references indexed in Scilit:
- A simple algorithm for shape from shadingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The direct computation of height from shadingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Object-centered surface reconstruction: Combining multi-image stereo and shadingInternational Journal of Computer Vision, 1995
- Shape from shading with a linear triangular element surface modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Estimation of illuminant direction, albedo, and shape from shadingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Fast shape from shadingCVGIP: Image Understanding, 1991
- Height and gradient from shadingInternational Journal of Computer Vision, 1990
- Improved methods of estimating shape from shading using the light source coordinate systemArtificial Intelligence, 1985
- Numerical shape from shading and occluding boundariesArtificial Intelligence, 1981
- Theory for Off-Specular Reflection From Roughened Surfaces*Journal of the Optical Society of America, 1967