Home
Resource
Learning human facial performance
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(18.94 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Pham, Hai. Learning human facial performance. Retrieved from https://doi.org/doi:10.7282/t3-j494-3c36

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleLearning human facial performance
NamePham, Hai (author); Pavlovic, Vladimir (chair); Metaxas, Dimitris (internal member); Elgammal, Ahmed (internal member); Luo, Jiebo (outside member); Rutgers University; School of Graduate Studies
Date Created2019
Other Date2019-01 (degree)
SubjectComputer Science, Human face recognition (Computer science)
Extent1 online resource (110 pages) : illustrations
DescriptionHuman faces convey a large range of semantic meaning through facial expressions, which reflect both actions and affective states. More importantly, in the coming age of artificial intelligence and virtual persona, facial expressions can serve as a two-way communicative interface between human and machine. In this dissertation, we study two aspects of face and facial expression modeling: the analysis and reconstruction of human facial expressions via interpretable 3D blendshape representation from different input modalities, and the reversed problem in which we train a model to hallucinate coherent facial expressions directly given any arbitrary portrait and facial action parameters.

First, we present a real-time robust 3D face tracking framework from RGBD videos, driven by an efficient and flexible 3D shape regressor, capable of tracking head pose, facial actions and on-the-fly identity adaptation in extreme instances. Second, we introduce a series of recurrent neural networks to predict facial action intensities from speech for real-time animation. Finally, we present a novel deep generative neural network that can directly manipulate image pixels of a portrait to make the unseen subject express various emotions controlled by continuous facial action unit coefficients, while maintaining her personal characteristics. Our model enables flexible, effortless facial expression editing.
NotePh.D.
NoteIncludes bibliographical references
Noteby Hai Xuan Pham
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/t3-j494-3c36
Languageeng
CollectionSchool of Graduate Studies Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.1
Rutgers University Libraries - Copyright ©2023