ML Anthology

Height Recovery from Intensity Gradient

Ruo Zhang, Mubarak Shah
CVPR 1994 pp. 508-513
doi:10.1109/CVPR.1994.323874 /cvpr/1994/zhang1994cvpr-height/

Abstract

Unlike existing global shape-from-shading algorithms which involve the brightness constraint in their formulation, we propose a new algorithm which replaces the brightness constraint by an intensity gradient constraint. This is a global approach which obtains the solution by the minimization of an error function over the entire image. Through the linearization of the reflectance map and the discretization of the surface gradient, the intensity gradient can be expressed as a linear function of the surface height. A quadratic error function, which involves the intensity gradient constraint and the traditional smoothness constraint, is minimized efficiently by solving a sparse linear system using the multigrid technique. Neither the information at singular points nor the information at occluding boundaries is needed for the initialization.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Zhang and Shah. "Height Recovery from Intensity Gradient." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323874

Markdown

[Zhang and Shah. "Height Recovery from Intensity Gradient." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/zhang1994cvpr-height/) doi:10.1109/CVPR.1994.323874

BibTeX

@inproceedings{zhang1994cvpr-height,
  title     = {{Height Recovery from Intensity Gradient}},
  author    = {Zhang, Ruo and Shah, Mubarak},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {508-513},
  doi       = {10.1109/CVPR.1994.323874},
  url       = {https://mlanthology.org/cvpr/1994/zhang1994cvpr-height/}
}