Feature Point Based Mesh Deformation Applied to MPEG-4 Facial Animation

Kshirsagar, Sumedha; Garchery, S.; Magnenat‐Thalmann, Nadia

doi:10.1007/978-0-306-47002-8_3

Cited by 44 publications

(34 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Starting with Parke's work [23], several types of face models have been developed, which can be classified either as parametric [23]- [25] or muscle-based [26]- [32]. Parametric approaches represent the facial model with specific control parameters and animate by simple mesh or parameter interpolation, whereas muscle-based approaches attempt to represent to some degree of accuracy the anatomic structure of the face and simulate the behavior of muscles to animate the model.…”

Section: Related Workmentioning

confidence: 99%

“…In addition, an MPEG-4 [25], [33] compliant interface was also implemented. The details of this facial model are described in Section V.…”

Section: Related Workmentioning

confidence: 99%

“…The influence area is a list of vertices that are affected by the muscle, as well as the corresponding weight for each vertex, in a manner akin to Kshirsagar [25]. The list of vertices associated to each muscle is determined once, when the generic face model is modified to generate a new model for a particular speaker, and subsequently stored in a data structure.…”

Section: A Generic Facial Modelmentioning

confidence: 99%

See 2 more Smart Citations

Speech-driven facial animation with realistic dynamics

Gutierrez‐Osuna

Kakumanu

Esposito

et al. 2005

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-This paper presents an integral system capable of generating animations with realistic dynamics, including the individualized nuances, of three-dimensional (3-D) human faces driven by speech acoustics. The system is capable of capturing short phenomena in the orofacial dynamics of a given speaker by tracking the 3-D location of various MPEG-4 facial points through stereovision. A perceptual transformation of the speech spectral envelope and prosodic cues are combined into an acoustic feature vector to predict 3-D orofacial dynamics by means of a nearest-neighbor algorithm. The Karhunen-Loéve transformation is used to identify the principal components of orofacial motion, decoupling perceptually natural components from experimental noise. We also present a highly optimized MPEG-4 compliant player capable of generating audio-synchronized animations at 60 frames/s. The player is based on a pseudo-muscle model augmented with a nonpenetrable ellipsoidal structure to approximate the skull and the jaw. This structure adds a sense of volume that provides more realistic dynamics than existing simplified pseudo-muscle-based approaches, yet it is simple enough to work at the desired frame rate. Experimental results on an audiovisual database of compact TIMIT sentences are presented to illustrate the performance of the complete system. Index Terms-face image analysis and synthesis, lip synchronization, 3-D audio/video processing.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In addition, an MPEG-4 [25], [33] compliant interface was also implemented. The details of this facial model are described in Section V.…”

Section: Related Workmentioning

confidence: 99%

Section: A Generic Facial Modelmentioning

confidence: 99%

See 1 more Smart Citation

Speech-driven facial animation with realistic dynamics

Gutierrez‐Osuna

Kakumanu

Esposito

et al. 2005

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…Facial dynamics are considered during the expression change, and appropriate temporal transition functions are selected for facial animation. We use MPEG-4 Facial Animation Parameters as low level facial deformation parameters [12]. However, for defining the visemes and expressions, we use the Principal Components (PCs) [13].…”

Section: Visual Front-endmentioning

confidence: 99%

A Model for Personality and Emotion Simulation

Egges

Kshirsagar

Magnenat‐Thalmann

2003

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. This paper describes a generic model for personality, mood and emotion simulation for conversational virtual humans. We present a generic model for describing and updating the parameters related to emotional behaviour. Also, this paper explores how existing theories for appraisal can be integrated into the framework. Finally we describe a prototype system that uses the described models in combination with a dialogue system and a talking head with synchronised speech and facial expressions.

show abstract

“…The details of the facial deformation algorithm are explained in [27]. For defining the visemes and expressions, we use the technique described by Kshirsagar et al [28].…”

Section: Believable Facial Animationmentioning

confidence: 99%

Believability and Interaction in Virtual Worlds

Magnenat‐Thalmann

Kim

Egges

et al.

11th International Multimedia Modelling Conference

View full text Add to dashboard Cite

In this paper we present a discussion about believability for Virtual Environments, emotional simulation and also Embodied Conversational Agents (ECAs). We will discuss about the definition of believability and the three elements of believability environments (immersion, presentation and interaction). We also present a discussion about believability and interfaces. Finally, ECA, emotional and personnality simulation are explained and presented.

show abstract

Feature Point Based Mesh Deformation Applied to MPEG-4 Facial Animation

Cited by 44 publications

References 8 publications

Speech-driven facial animation with realistic dynamics

Speech-driven facial animation with realistic dynamics

A Model for Personality and Emotion Simulation

Believability and Interaction in Virtual Worlds

Contact Info

Product

Resources

About