Home
Resource
Facial expression transfer by using 3D-aware expression flow
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(17.97 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Yang, Fei. Facial expression transfer by using 3D-aware expression flow. Retrieved from https://doi.org/doi:10.7282/T35B00J8

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleFacial expression transfer by using 3D-aware expression flow
NameYang, Fei (author); Metaxas, Dimitris (chair); Eliassi-Rad, Tina (internal member); Bekris, Kostas (internal member); Huang, Xiaolei (outside member); Rutgers University; Graduate School - New Brunswick
Date Created2013
Other Date2013-10 (degree)
SubjectComputer Science, Facial expression, Facial expression--Testing
Extentxiv, 93 p. : ill.
DescriptionWe study the problem of transferring facial expressions from one face to another. Direct copying and blending face components using existing methods results in semantically unnatural composites, since expression is a global effect and a local face component in one expression is often incompatible with the shape and other components in another expression. To solve this problem we present the expression flow method, which is a 2D flow field that can warp the target face globally. We develop a shape fitting algorithm, which jointly constructs 3D face shapes to the input images with the same identity but different expressions. The expression flow is computed by projecting the difference between the two 3D shapes to 2D image plane. We apply our algorithms in several applications including face compositing, face morphing, video stitching, and facial expression exaggeration. Our system is able to generate faces with much higher fidelity than existing methods.
NotePh.D.
NoteIncludes bibliographical references
NoteIncludes vita
Noteby Fei Yang
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/T35B00J8
Languageeng
CollectionGraduate School - New Brunswick Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024