Art-directed muscle simulation for high-end facial animation
Abstract/Contents
- Abstract
- This dissertation presents a system for generating high-end facial animation using muscle simulation. While the rendering of still faces has become quite realistic, facial animation techniques still suffer from a variety of artifacts. The traditional blendshape approach for animating faces often suffers from visual artifacts and requires the time-consuming process of sculpting high-quality facial shapes for a variety of expressions. Alternatively, one could build an anatomically accurate face simulation model and actuate facial muscles to deform the flesh and skin. However, the results are often of lower quality compared to those obtained from other production facial animation techniques. This dissertation addresses these issues by describing an algorithm to automatically build anatomical face simulation models as well as a new framework for the simulation of these models that significantly improves the quality of the results allowing for the immediate mainstream use of anatomical face simulation models in a high-end production quality pipeline.
Description
Type of resource | text |
---|---|
Form | electronic; electronic resource; remote |
Extent | 1 online resource. |
Publication date | 2016 |
Issuance | monographic |
Language | English |
Creators/Contributors
Associated with | Cong, Matthew Deying |
---|---|
Associated with | Stanford University, Department of Computer Science. |
Primary advisor | Fedkiw, Ronald P, 1968- |
Thesis advisor | Fedkiw, Ronald P, 1968- |
Thesis advisor | Bhat, Kiran |
Thesis advisor | Hanrahan, P. M. (Patrick Matthew) |
Advisor | Bhat, Kiran |
Advisor | Hanrahan, P. M. (Patrick Matthew) |
Subjects
Genre | Theses |
---|
Bibliographic information
Statement of responsibility | Matthew Deying Cong. |
---|---|
Note | Submitted to the Department of Computer Science. |
Thesis | Thesis (Ph.D.)--Stanford University, 2016. |
Location | electronic resource |
Access conditions
- Copyright
- © 2016 by Matthew Deying Cong
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...