Curvature consistency for shape-from-shading

Authors:
Fabio Sartori;Edwin R. Hancock
Affiliations:
Department of Computer Science, University of York, York, UK;Department of Computer Science, University of York, York, UK
Venue:
SCIA'03 Proceedings of the 13th Scandinavian conference on Image analysis
Year:
2003

Citing 7
Cited 0

On shape from shading

Computer Vision, Graphics, and Image Processing
Solid shape

Solid shape
Inferring Surface Trace and Differential Structure from 3-D Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape from shading

Shape from shading
Height and gradient from shading

International Journal of Computer Vision
New Constraints on Data-Closeness and Needle Map Consistency for Shape-from-Shading

IEEE Transactions on Pattern Analysis and Machine Intelligence
What is the set of images of an object under all possible lighting conditions?

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a new curvature consistency method for shape-from-shading. Our idea is to combine evidence for the best surface normal direction. To do this we transport surface normals across the surface using a local estimate of the Hessian matrix. The evidence combination process uses the normal curvature to compute a weighted average surface normal direction. We expriment with the resulting shape-from-shading method on a variety of real world synthetic data.