Use of Four Surface Normal Approximations and Optimization of Light Direction for Robust Shape Reconstruction from Single Images

Authors:
Affiliations:
Venue:
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Year:
2004

Citing 4
Cited 1

Estimation of Illuminant Direction, Albedo, and Shape from Shading

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking level sets by level sets: a method for solving the shape from shading problem

Computer Vision and Image Understanding
New Constraints on Data-Closeness and Needle Map Consistency for Shape-from-Shading

IEEE Transactions on Pattern Analysis and Machine Intelligence
Incorporating Illumination Constraints in Deformable Models

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Quaternion-based albedo recovery for shape reconstruction

ICNVS'10 Proceedings of the 12th international conference on Networking, VLSI and signal processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a robust shape-from-shading method, by which we areable to estimate accurate shapes from single shading imageswhose slant angles are relatively large. First, we derive fouriterative relations for shape estimation by applying the Jacobiýsiterative method and by using four approximations of the surfacenormal, and combine them with weights to get a single relation.This enables us to achieve stable shape estimation with a fairdegree of accuracy. Second, we optimize the light direction inslant angle through the eigenvalue analysis for the matrix of thecombined iterative relation, to reduce the remaining distortions.Numerical examples using both synthetic and real images showthe usefulness of the method.