Model-based ambient occlusion for inverse rendering

Authors:
Oswald Aldrian;William A. P. Smith
Affiliations:
Department of Computer Science, University of York, UK;Department of Computer Science, University of York, UK
Venue:
ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part I
Year:
2012

Citing 8
Cited 0

A morphable model for the synthesis of 3D faces

Proceedings of the 26th annual conference on Computer graphics and interactive techniques
A signal-processing framework for inverse rendering

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Estimating 3D Shape and Texture Using Pixel Intensity, Edges, Specular Highlights, Texture Constraints and a Prior

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Face Recognition from a Single Training Image under Arbitrary Unknown Lighting Using Spherical Harmonics

IEEE Transactions on Pattern Analysis and Machine Intelligence
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)

Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Recovering Facial Shape Using a Statistical Model of Surface Normal Direction

IEEE Transactions on Pattern Analysis and Machine Intelligence
A 3D Face Model for Pose and Illumination Invariant Face Recognition

AVSS '09 Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance
Physically Based Rendering, Second Edition: From Theory To Implementation

Physically Based Rendering, Second Edition: From Theory To Implementation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel framework to inverse render faces in arbitrary complex illumination with a 3D morphable model. Compared to previously introduced methods, we specifically take self-occlusion into account and demonstrate that this improves the fitting accuracy by about 10%. Motivated by this observation, we design a generative statistical model of ambient occlusion. We examine generalisation error of the model and propose two ways how ambient occlusion can be inferred from shape. The proposed methods are incorporated into an existing framework to inverse render faces. We show qualitative and quantitative results for the proposed extensions and compare it with a reference method.