DOI: https://doi.org/10.15368/theses.2021.104
Available at: https://digitalcommons.calpoly.edu/theses/2315
Date of Award
6-2021
Degree Name
MS in Computer Science
Department/Program
Computer Science
College
College of Engineering
Advisor
Zoë Wood
Advisor Department
Computer Science
Advisor College
College of Engineering
Abstract
Human communications rely on facial expression to denote mood, sentiment, and intent. Realistic facial animation of computer graphic models of human faces can be difficult to achieve as a result of the many details that must be approximated in generating believable facial expressions. Many theoretical approaches have been researched and implemented to create more and more accurate animations that can effectively portray human emotions. Even though many of these approaches are able to generate realistic looking expressions, they typically require a lot of artistic intervention to achieve a believable result. To reduce the intervention needed to create realistic facial animation, new approaches that utilize machine learning are being researched to reduce the amount of effort needed to generate believable facial animations. This survey paper summarizes over 20 research papers related to facial animation and compares the traditional animation approaches to newer machine learning methods as well as highlights the strengths, weaknesses, and use cases of each different approach.