Facial expression cloning: using expressive ratio image and FAP to texture conversion
Pei-Wei Hsu, Yao-den Chang, Chao-Kuei Hsieh, Yiang-Chang Chen · 2004
The visual perception of model-based coding is usually not good enough. We develop a facial expression cloning system which can make a 3-D facial model lifelike, and transfer a person's subtle facial change to another's by using the expression ratio image (ERI). An expressive 3-D facial model will be shown. On the other hand, we intend to achieve an intelligent system which can make a 3-D facial model lifelike and doesn't need to transmit any more information, i.e., we intend to model the MPEG-4 facial animation parameters (FAP) to ratio image conversion. In order that each FAP follows a unique ratio image, the FAP and the expression ratio image have to be considered as jointly distributed. Thus, an automated system which achieves the desired lifelike 3-D facial model is developed.