3D surface reconstruction based on one non-symmetric face image

Authors:
Li Feng;Jianhuang Lai;Lei Zhang
Affiliations:
Center of Computer Vision, Sun Yat-sen University;Center of Computer Vision, Sun Yat-sen University;Center of Computer Vision, Sun Yat-sen University
Venue:
SINOBIOMETRICS'04 Proceedings of the 5th Chinese conference on Advances in Biometric Person Authentication
Year:
2004

Citing 7
Cited 0

A Method for Enforcing Integrability in Shape from Shading Algorithms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of Illuminant Direction, Albedo, and Shape from Shading

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape from Shading: A Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Statistical approach to shape from shading: Reconstruction of three-dimensional face surfaces from single two-dimensional images

Neural Computation
Local Shading Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape from intensity gradient

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shape from shading (SFS) is an important research domain in the Computer Vision, in which the technology making use of the change in image brightness of an object to determine the relative surface depth receives a lot of attention Now many algorithms have been developed to perform the goal, especially the model-based symmetric Shape-from-Shading approach presented by Zhao works well, but the symmetry supposition limits the application of the approach In order to get rid of the limit, we have improved the traditional Jacobi's iterative method by making use of the brightness constraint and the smoothness constraint to implement the face 3D surface reconstruct, and we have gave the synthesis of the prototype image under the single frontal light source to verify the validity of the algorithm.