Realtime performance-based facial animation

Weise, Thibaut; Bouaziz, Samir; Li, Hao; Pauly, Mark

doi:10.1145/1964921.1964972

Cited by 261 publications

(205 citation statements)

References 40 publications

Supporting

Mentioning

203

Contrasting

Unclassified

Order By: Relevance

“…As we will see in the following, rigs provide the interface between the manual inputs of an animator who authors an animation on a key-frame basis [3,5]. Alternatively, the interface between an interactive input method and a virtual or real puppet generates low-level animation data [8,10]. In fact, most animation authoring pipelines can be classified according to two dimensions: input type (manual edit vs captured motion) and usage (online puppetry vs offline animation).…”

Section: Related Workmentioning

confidence: 99%

“…For example, see [8] or the Dynamixyz 2 systems. When it includes face, Motion Capture [20] is often referred to as performance capture.…”

Section: Online Puppetry and Performance Capturementioning

confidence: 99%

“…The animation workflow presented in this paper is based on the technology developed by Weise et al [8], where a facial expression is described through a weights vector of a set of blendshapes. Section 4 describes the mapping method which translates the weights vector into a configuration of the control rig.…”

Section: Online Puppetry and Performance Capturementioning

confidence: 99%

“…The details of its underlying implementation can be seen in [8]. Faceshift is based on the OpenNI 7 middleware, which guarantees compatibility with a wide range of Kinect-like hardware available on the consumer market.…”

Section: Architecturementioning

confidence: 99%

“…capture of facial expressions [7,8]. In performance capture the animator can use his own face to drive the animation of an arbitrary avatar.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Evaluation of a Facial Animation Authoring Pipeline Seamlessly Supporting Performance Capture and Manual Key-pose Editing

Nunnari¹,

Héloir²

2015

EAI Endorsed Transactions on Creative Technologies

View full text Add to dashboard Cite

In this paper, we present an architecture following a novel animation authoring pipeline seamlessly supporting performance capture and manual editing of key-frames animation. This pipeline allows novice users to record and author sophisticated facial animations in a fraction of the time that would be required using traditional animation tools. This approach paves the way towards novel animation pipelines which seamlessly merge the roles of the animator and the actor. The second contribution is a method assessing a facial retargeting system, we conducted a user study where participants assessed the emotions conveyed by the facial expression displayed in the control and the authored animation. Contrary to existing evaluation methods, it factors out possible misinterpretations of the intended emotion and focuses on assessing the retargeting quality.

show abstract

Section: Related Workmentioning

confidence: 99%

“…For example, see [8] or the Dynamixyz 2 systems. When it includes face, Motion Capture [20] is often referred to as performance capture.…”

Section: Online Puppetry and Performance Capturementioning

confidence: 99%

Section: Online Puppetry and Performance Capturementioning

confidence: 99%

Section: Architecturementioning

confidence: 99%

“…capture of facial expressions [7,8]. In performance capture the animator can use his own face to drive the animation of an arbitrary avatar.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Evaluation of a Facial Animation Authoring Pipeline Seamlessly Supporting Performance Capture and Manual Key-pose Editing

Nunnari¹,

Héloir²

2015

EAI Endorsed Transactions on Creative Technologies

View full text Add to dashboard Cite

show abstract

3D Face Modeling

Amor

Ardabilian

Chen

2013

3D Face Modeling, Analysis and Recognition

View full text Add to dashboard Cite

Video‐driven state‐aware facial animation

Zhang

Liu

et al. 2012

Computer Animation & Virtual

View full text Add to dashboard Cite

It is important in computer animation to synthesize expressive facial animation for avatars from videos. Some traditional methods track a set of semantic feature points on the face to drive the avatar. However, these methods usually suffer from inaccurate detection and sparseness of the feature points and fail to obtain high-level understanding of facial expressions, leading to less expressive and even wrong expressions on the avatar. In this paper, we propose a state-aware synthesis framework. Instead of simply fitting 3D face to the 2D feature points, we use expression states obtained by a set of lowcost classifiers (based on local binary pattern and support vector machine) on the face texture to guide the face fitting procedure. Our experimental results show that the proposed hybrid framework enjoys the advantages of the original methods based on feature point and the awareness of the expression states of the classifiers and thus vivifies and enriches the face expressions of the avatar.

show abstract

Realtime performance-based facial animation

Abstract: Figure 1: Our system captures and tracks the facial expression dynamics of the users (grey renderings) in realtime and maps them to a digital character (colored renderings) on the opposite screen to enable engaging virtual encounters in cyberspace.

Cited by 261 publications

References 40 publications

Evaluation of a Facial Animation Authoring Pipeline Seamlessly Supporting Performance Capture and Manual Key-pose Editing

Evaluation of a Facial Animation Authoring Pipeline Seamlessly Supporting Performance Capture and Manual Key-pose Editing

3D Face Modeling

Video‐driven state‐aware facial animation

Contact Info

Product

Resources

About