Separability of pose and expression in facial tracking and animation

Bascle, B.; Blake, A.

doi:10.1109/iccv.1998.710738

Cited by 64 publications

(57 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zhiwei Zhu and Qiang [39] derived a technique based on Singular Value Decomposition (SVD) [13] which can recover 3D face pose and facial expression simultaneously from a monocular video sequence in real time. This is the concept envisaged in their paper on 'Robust Real Time Face Pose and Facial Expression Recovery'.…”

Section: D Face Pose Recovery and Facial Expressionmentioning

confidence: 99%

Study of the Changing Trends in Facial Expression Recognition

Ravi¹,

Mahima²

2011

IJCA

View full text Add to dashboard Cite

Enrichment of knowledge becomes possible only through literature search on any topic of interest. It is true even in the case of 'Facial Expression Recognition'. So it is attempted to have a broad look into the origin and development of 'Facial Expression Recognition' in the recent past. It has been developed, into a topic of interest, only after the contributions made by Ekman and Friesen. Though there are many expressions yet to be recognized, significant contributions are made by many eminent scholars to identify the six primary emotions viz. happiness, sadness, fear, disgust, surprise and anger. In this paper, we attempted to bring to lime light some of the important contributions on the subject.

show abstract

Section: D Face Pose Recovery and Facial Expressionmentioning

confidence: 99%

Study of the Changing Trends in Facial Expression Recognition

Ravi¹,

Mahima²

2011

IJCA

View full text Add to dashboard Cite

show abstract

“…There are two main shortcomings of such an approach: firstly, it requires the set of interest points on each image to lie on static 3D surfaces of the scene; and secondly, the surfaces of the scene must be textured enough to allow interest points to be estimated. When we approach the problem of estimating 3D rigid facial motions from images, we find that the problem of estimating the rigid motion of a 3D surface with many instantaneous local deformations is usually due to local facial motions [1,5,8]. Furthermore, it is well known that the surface of the face is not textured enough.…”

Section: Introductionmentioning

confidence: 99%

3D Rigid Facial Motion Estimation from Disparity Maps

Blanca

Fuertes

Lucena

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This paper proposes an approach to estimate 3D rigid facial motions through a stereo image sequence. The approach uses a disparity space as the main space in order to represent all the 3D information. A robust algorithm based on the RANSAC approach is used to estimate the rigid motions through the image sequence. The disparity map is shown to be a robust feature against local motions of the surface and is therefore a very good alternative to the traditional use of the set of interest points.

show abstract

“…Feature-based procedures were the first tracking algorithms to be introduced. They are based on tracking a discrete set of texture elements such as eye or nose corners and the contours of expressive regions (eyes, eyelids or mouth) [2,14]. They can only estimate the motion of textured regions and, therefore, they provide sparse information about the deformation of the face.…”

Section: Introductionmentioning

confidence: 99%

Performance driven facial animation using illumination independent appearance-based tracking

Buenaposada

Muñoz

Baumela

2006

18th International Conference on Pattern Recognition (ICPR'06)

View full text Add to dashboard Cite

We introduce a procedure to estimate human face high level animation parameters from a marker-less image sequence in presence of strong illumination changes. We use an efficient appearance-based tracker to stabilise face images and estimate illumination variation. This is achieved by using an appearance model composed by two independent linear subspaces modelling face deformation and illumination changes respectively. The system is very simple to train and is able to re-animate a 3D face model in real-time.

show abstract

Separability of pose and expression in facial tracking and animation

Cited by 64 publications

References 11 publications

Study of the Changing Trends in Facial Expression Recognition

Study of the Changing Trends in Facial Expression Recognition

3D Rigid Facial Motion Estimation from Disparity Maps

Performance driven facial animation using illumination independent appearance-based tracking

Contact Info

Product

Resources

About