MPEG-4 based animation with face feature tracking

Goto, Taro; Escher, M.; Zanardi, Christian; Magnenat‐Thalmann, Nadia

doi:10.1007/978-3-7091-6423-5_9

Cited by 20 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the computational cost is rather low. The FBA parameters, both FPs either FAPs, can be extracted automatically from visual, audio or motion capture systems [4,3,10,11], therefore they can be properly compressed in a data stream. Combined with facial feature tracking, MPEG-4 FBA talking heads can potentially be used for a very low bitrate visual communication in a model-based coding scenario (teleconferencing, games, web interfaces) [5,15].…”

Section: Discussionmentioning

confidence: 99%

Fast facial motion cloning in MPEG-4

Fratarcangeli

Schaerf

2005

ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.

View full text Add to dashboard Cite

Facial Motion Cloning (FMC) is the technique employedto transfer the motion of a virtual face (namely, the source) to a mesh representing another face (the target), generally having a different geometry and topology. We present a novel FMC method relying on the combination of the Radial Basis Functions (RBF) based scattered data interpolation with the encoding capabilities of the MPEG-4 Facial and Body Animation (FBA) international standard. Starting from a manually picked set of correspondences, we find a scattered data interpolation function that precisely fit the source face mesh into the target one. Then, all the MPEG-4 FBA basic movements (encoded as morph targets) of the source face are deformed using the same function and the deformations are mapped to the corresponding vertices of the target mesh. By doing this, we obtain, in a straightforward and simple way, the animatable MPEG-4 compliant version of the target face in a short amount of time.

show abstract

Section: Discussionmentioning

confidence: 99%

Fast facial motion cloning in MPEG-4

Fratarcangeli

Schaerf

2005

ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.

View full text Add to dashboard Cite

show abstract

“…Specifically, for the multimedia communication and very low bit rate applications, the MPEG-4 standard (ISO/IEC, 2000) defines a set of 68 facial animation parameters (FAPs) each of which specifies features points and geometric transformation applied on them. Ostermann (1998), Zhong (1998) and Goto et al (1999) used these FAPs to control their facial animation system. However, the ad hoc parametric models have been developed with little theoretical basis and without careful attention to facial anatomy.…”

Section: Previous Workmentioning

confidence: 99%

Modeling and animation of individualized faces for 3D facial expression synthesis

Prakash

Sung

2003

Int J Imaging Syst Tech

View full text Add to dashboard Cite

This article presents new methods for realistic and fast 3D facial expression synthesis based on an individualized face model constructed from the anatomical perspective. The face model has a 3D structure of anatomically motivated facial skin, muscles, and skull. We start from a highly accurate facial mesh reconstructed from the individual face measurements. By taking as input a collection of reflectance images covering the face, the view-based texture blending method automatically generates a comprehensive texture map for photorealistic rendering. Based on the reconstructed facial mesh, a deformable multilayer skin model is developed to simulate the dynamic behavior of the skin by taking into account the nonlinear stress-strain relationship and incompressibility of the skin. We develop a muscle modeling process that includes three kinds of forcebased facial muscle model to simulate facial muscle contraction. The 3D face model incorporates a skull structure which extends the scope of facial motion, facilitates facial muscle construction and constrains skin deformation. Based on the facial action coding system, various facial expressions are synthesized by the contraction of a set of facial muscles. Lagrangian mechanics governs the dynamics, dictating the deformation of facial skin in response to the contraction of muscles. For computational efficiency, we devise an adaptive computation algorithm for the numerical simulation. It uses either a semi-implicit integration scheme or a quasi-static solver to compute the relaxation of the facial mesh by traversing the designed data structures in a breadth-first order. The resulting system enables us to construct realistic face models of living humans and to synthesize facial expressions in real time.

show abstract

“…Since the pioneering work of Parke [1] in the early 70s, researchers have investigated techniques to generate realistic face models and animation [2]. Early works restricted them-selves to geometric models and simulation methods, such as key-frame interpolation animation [1,3], parametric models [4][5][6][7][8], abstract muscle actions [9][10][11] and performance driven animation [12,13]. To extend the range of possible facial deformations, during the last decade, some researchers turned to physically-based methods, using either a particle system or a continuous system.…”

Section: Background and Previous Workmentioning

confidence: 99%

Efficient Modeling of An Anatomy‐Based Face and Fast 3D Facial Expression Synthesis

Zhang

Prakash

Sung

2003

Computer Graphics Forum

View full text Add to dashboard Cite

This paper presents new methods for efficient modeling and animation of an hierarchical facial model that conforms to the human face anatomy for realistic and fast 3D facial expression synthesis. The facial model has a skin–muscle–skull structure. The deformable skin model directly simulates the nonlinear visco‐elastic behavior of soft tissue and effectively prevents model collapse. The construction of facial muscles is achieved by using an efficient muscle mapping approach. Based on a cylindrical projection of the texture‐mapped facial surface and wire‐frame skin and skull meshes, this approach ensures different muscles to be located at the anatomically correct positions between the skin and skull layers. For computational efficiency, we devise an adaptive simulation algorithm which uses either a semi‐implicit integration scheme or a quasi‐static solver to compute the relaxation by traversing the designed data structures in a breadth‐first order. The algorithm runs in real‐time and has successfully synthesized realistic facial expressions. ACM CSS: I.3.5 Computer Graphics: Computational Geometry and Object Modelling—physically based modelling; I.3.7 Computer Graphics: Three‐Dimensional Graphics and Realism—animation;

show abstract

MPEG-4 based animation with face feature tracking

Cited by 20 publications

References 1 publication

Fast facial motion cloning in MPEG-4

Fast facial motion cloning in MPEG-4

Modeling and animation of individualized faces for 3D facial expression synthesis

Efficient Modeling of An Anatomy‐Based Face and Fast 3D Facial Expression Synthesis

Contact Info

Product

Resources

About