Face relighting under arbitrary unknown illumination conditions based on estimated light source direction

Authors:
Heechul Han;Kwanghoon Sohn
Affiliations:
Yonsei University, Seodaemun-gu, Seoul, Korea;Yonsei University, Seodaemun-gu, Seoul, Korea
Venue:
VIIP '07 The Seventh IASTED International Conference on Visualization, Imaging and Image Processing
Year:
2007

Citing 9
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multidimensional binary search trees used for associative searching

Communications of the ACM
From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple Illuminant Direction Detection with Application to Image Synthesis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Estimation of Multiple Directional Light Sources for Synthesis of Mixed Reality Images

PG '02 Proceedings of the 10th Pacific Conference on Computer Graphics and Applications
Multiple Light Source Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Synthesis and Recognition from a Single Image under Arbitrary Unknown Lighting Using a Spherical Harmonic Basis Morphable Model

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Multiple Light Sources and Reflectance Property Estimation Based on a Mixture of Spherical Distributions

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Estimation of 3D faces and illumination from single photographs using a bilinear illumination model

EGSR'05 Proceedings of the Sixteenth Eurographics conference on Rendering Techniques

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a novel method to estimate the light source direction and relight a face texture image of a single 3D model obtained under arbitrary unknown illumination conditions. We create a virtual irradiance sphere to detect the light source direction from a given illuminated texture image using both normal vector mapping and weighted bilinear interpolation. We then create a relighting equation with estimated ambient intensity and diffuse intensity obtained by the least square method. We provide a series of experiments on both light source estimation and relighting to show that our method is effective in restoring the shading and shadows areas of a face texture image. Our approach for face relighting should be used for illuminant invariant face recognition applications.