3D Reconstruction and Synthesis of Facial Expressions using a Manifold Alignment Framework

MPhil Thesis Defence


Title: "3D Reconstruction and Synthesis of Facial Expressions
using a Manifold Alignment Framework"

By

Mr. Lap-Fai Yu


Abstract

The capture, reconstruction and synthesis of facial expressions often involves 
specialized hardware support and considerable computation time. This prohibits 
its widespread deployment and use in real-time applications. In this paper, we 
aim at tackling this limitation via a learning-based approach, which is 
efficient and requires only modest hardware support. Our approach is based on a 
semi-supervised manifold alignment framework, where feature points extracted 
from 2D face images are aligned with data expressed as morph-target values for 
a 3D face model.  By applying a kernel embedding method known as kernel 
locality preserving projections (KLPP) and a method for solving the pre-image 
problem in kernel methods, our framework is capable of handling nonlinearity 
and is defined everywhere. Experiments are conducted to demonstrate two 
possible applications of our proposed framework: 3D reconstruction of facial 
expressions and dynamic synthesis of facial expression sequences.


Date:				Friday, 13 March 2009

Time:				4:30p.m.-6:30p.m.

Venue:				Room 5504
 				Lifts 25-26

Committee Members:		Prof. Dit-Yan Yeung (Supervisor)
 				Prof. Long Quan (Chairperson)
 				Dr. Pedro Sander


**** ALL are Welcome ****