ML Anthology

Data-Driven Shape-from-Shading Using Curvature Consistency

Philip L. Worthington, Edwin R. Hancock
CVPR 1999 pp. 1287-1293
doi:10.1109/CVPR.1999.786953 /cvpr/1999/worthington1999cvpr-data/

Abstract

This paper makes two contributions to the problem of needle-map recovery using shape-from-shading. Firstly, we provide a geometric update procedure which allows the image irradiance equation to be satisfied as a hard-constraint. This improves the data-closeness of the recovered needle-map. Secondly, we consider how topographic constraints can be lured to impose local consistency on the recovered needle-map. We present several alternative curvature consistency models, and provide an experimental assessment of the new shape-from-shading framework on both real-world images and synthetic images with known ground-truth surface-normals. The main conclusion drawn from our analysis is that the new framework allows rapid development of more appropriate constraints on the SFS problem.

CVPR Semantic Scholar

Cite

Text

Worthington and Hancock. "Data-Driven Shape-from-Shading Using Curvature Consistency." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999. doi:10.1109/CVPR.1999.786953

Markdown

[Worthington and Hancock. "Data-Driven Shape-from-Shading Using Curvature Consistency." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1999.](https://mlanthology.org/cvpr/1999/worthington1999cvpr-data/) doi:10.1109/CVPR.1999.786953

BibTeX

@inproceedings{worthington1999cvpr-data,
  title     = {{Data-Driven Shape-from-Shading Using Curvature Consistency}},
  author    = {Worthington, Philip L. and Hancock, Edwin R.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1999},
  pages     = {1287-1293},
  doi       = {10.1109/CVPR.1999.786953},
  url       = {https://mlanthology.org/cvpr/1999/worthington1999cvpr-data/}
}