Facial Expression Animation Research Articles

A nonparametric regression model for virtual humans generation

In this paper, we propose a novel nonparametric regression model to generate virtual humans from still images for the applications of next generation environments (NG). This model automatically synthesizes deformed shapes of characters by using kernel regression with elliptic radial basis functions (ERBFs) and locally weighted regression (LOESS). Kernel regression with ERBFs is used for representing the deformed character shapes and creating lively animated talking faces. For preserving patterns within the shapes, LOESS is applied to fit the details with local control. The results show that our method effectively simulates plausible movements for character animation, including body movement simulation, novel views synthesis, and expressive facial animation synchronized with input speech. Therefore, the proposed model is especially suitable for intelligent multimedia applications in virtual humans generation.

Facial expression animation overview

This paper reviews the main approaches to the human facial expression animation used in computer science and robotics. They rely on one-dimensional pictures or video sequences which describe the human face in different emotional states. The synthesis of various expressions is achieved by manipulations of the geometry of the three-dimensional object which result in the surface of the object being deformed. As it is presented in the paper the face is a specific carrier of information and as a strong visual stimulus it attracts most of the attention during the conversation and thus the facial expression is an easily accessible and credible transmitter of emotional states of the man, see Thomaz et al. [2008]. Research in the field of the human facial expressions, including search of factors that affect the emotional states interpretation has contributed to the improvement of the communication between people and machines. In the section 4 main techniques of various approaches are compared from the point of view of efficiency, applicability, complexity etc.

Humanoid Audio–Visual Avatar With Emotive Text-to-Speech Synthesis

Emotive audio-visual avatars are virtual computer agents which have the potential of improving the quality of human-machine interaction and human-human communication significantly. However, the understanding of human communication has not yet advanced to the point where it is possible to make realistic avatars that demonstrate interactions with natural-sounding emotive speech and realistic-looking emotional facial expressions. In this paper, We propose the various technical approaches of a novel multimodal framework leading to a text-driven emotive audio-visual avatar. Our primary work is focused on emotive speech synthesis, realistic emotional facial expression animation, and the co-articulation between speech gestures (i.e., lip movements) and facial expressions. A general framework of emotive text-to-speech (TTS) synthesis using a diphone synthesizer is designed and integrated into a generic 3-D avatar face model. Under the guidance of this framework, we therefore developed a realistic 3-D avatar prototype. A rule-based emotive TTS synthesis system module based on the Festival-MBROLA architecture has been designed to demonstrate the effectiveness of the framework design. Subjective listening experiments were carried out to evaluate the expressiveness of the synthetic talking avatar.

Dynamic facial expressions of emotion induce representational momentum

Two experiments were conducted to explore whether representational momentum (RM) emerges in the perception of dynamic facial expression and whether the velocity of change affects the size of the effect. Participants observed short morphing animations of facial expressions from neutral to one of the six basic emotions. Immediately afterward, they were asked to select the last images perceived. The results of the experiments revealed that the RM effect emerged for dynamic facial expressions of emotion: The last images of dynamic stimuli that an observer perceived were of a facial configuration showing stronger emotional intensity than the image actually presented. The more the velocity increased, the more the perceptual image of facial expression intensified. This perceptual enhancement suggests that dynamic information facilitates shape processing in facial expression, which leads to the efficient detection of other people's emotional changes from their faces.

Facial animation by optimized blendshapes from motion capture data

AbstractThis paper presents a labor‐saving method to construct optimal facial animation blendshapes from given blendshape sketches and facial motion capture data. At first, a mapping function is established between target “Marker Face” and performer's face by RBF interpolating selected feature points. Sketched blendshapes are transferred to performer's “Marker Face” by using motion vector adjustment technique. Then, the blendshapes of performer's “Marker Face” are optimized according to the facial motion capture data. At last, the optimized blendshapes are inversely transferred to target facial model. Apart from that, this paper also proposes a method of computing blendshape weights from facial motion capture data more accurately. Experiments show that expressive facial animation can be acquired. Copyright © 2008 John Wiley & Sons, Ltd.

얼굴 모션 추정과 표정 복제에 의한 3차원 얼굴 애니메이션

본 논문에서는 강건한 얼굴 포즈 추정과 실시간 표정제어가 가능한 비전 기반 3차원 얼굴 모델의 자동 표정 생성 방법 및 시스템을 제안한다. 기존의 비전 기반 3차원 얼굴 애니메이션에 관한 연구는 얼굴의 움직임을 나타내는 모션 추정을 반영하지 못하고 얼굴 표정 생성에 초점을 맞추고 있다. 그러나, 얼굴 포즈를 정확히 추정하여 반영하는 작업은 현실감 있는 얼굴 애니메이션을 위해서 중요한 이슈로 인식되고 있다. 본 연구 에서는 얼굴 포즈추정과 얼굴 표정제어가 동시에 가능한 통합 애니메이션 시스템을 제안 하였다. 제안된 얼굴 모델의 표정 생성 시스템은 크게 얼굴 검출, 얼굴 모션 추정, 표정 제어로 구성되어 있다. 얼굴 검출은 비모수적 HT 컬러 모델과 템플릿 매칭을 통해 수행된다. 검출된 얼굴 영역으로부터 얼굴 모션 추정과 얼굴 표정 제어를 수행한다. 얼굴 모션 추정을 위하여 3차원 실린더 모델을 검출된 얼굴 영역에 투영하고 광류(optical flow) 알고리즘을 이용하여 얼굴의 모션을 추정하며 추정된 결과를 3차원 얼굴 모델에 적용한다. 얼굴 모델의 표정을 생성하기 위해 특징점 기반의 얼굴 모델 표정 생성 방법을 적용한다. 얼굴의 구조적 정보와 템플릿 매칭을 이용하여 주요 얼굴 특징점을 검출하며 광류 알고리즘에 의하여 특징점을 추적한다. 추적된 특징점의 위치는 얼굴의 모션 정보와 표정 정보의 조합으로 이루어져있기 때문에 기하학적 변환을 이용하여 얼굴의 방향이 정면이었을 경우의 특징점의 변위인 애니메이션 매개변수(parameters)를 계산한다. 결국 얼굴 표정 복제는 두 개의 정합과정을 통해 수행된다. 애니메이션 매개변수 3차원 얼굴 모델의 주요 특징점(제어점)의 이동은 획득된 애니메이션 매개변수를 적용하여 수행하며, 정점 주위의 부가적 정점의 위치는 RBF(Radial Basis Function) 보간법을 통해 변형한다. 실험결과 본 논문에서 제안된 비전기반 애니메이션 시스템은 비디오 영상으로부터 강건한 얼굴 포즈 추정과 얼굴의 표정변화를 잘 반영하여 현실감 있는 애니메이션을 생성함을 입증할 수 있었다. This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

Synthesis of expressive facial animations: A multimodal caricatural mirror

This paper describes a natural and intuitive way to create expressive facial animations, using a novel approach based on the so-called ‘multimodal caricatural mirror’ (MCM). Taking as an input an audio-visual video sequence of the user’s face, the MCM generates a facial animation, in which the prosody and the facial expressions of emotions can either be reproduced or amplified. The user can thus simulate an emotion and see almost instantly the animation it produced, like with a regular mirror. In addition, the MCM also enables to amplify the emotions of selected parts of the input video sequence, leaving other parts unchanged. It therefore constitutes a novel approach to the design of very expressive facial animation, as the affective content of the animation can be modified by post-processing operations.

Rigid Head Motion in Expressive Speech Animation: Analysis and Synthesis

Rigid head motion is a gesture that conveys important nonverbal information in human communication, and hence it needs to be appropriately modeled and included in realistic facial animations to effectively mimic human behaviors. In this paper, head motion sequences in expressive facial animations are analyzed in terms of their naturalness and emotional salience in perception. Statistical measures are derived from an audiovisual database, comprising synchronized facial gestures and speech, which revealed characteristic patterns in emotional head motion sequences. Head motion patterns with neutral speech significantly differ from head motion patterns with emotional speech in motion activation, range, and velocity. The results show that head motion provides discriminating information about emotional categories. An approach to synthesize emotional head motion sequences driven by prosodic features is presented, expanding upon our previous framework on head motion synthesis. This method naturally models the specific temporal dynamics of emotional head motion sequences by building hidden Markov models for each emotional category (sadness, happiness, anger, and neutral state). Human raters were asked to assess the naturalness and the emotional content of the facial animations. On average, the synthesized head motion sequences were perceived even more natural than the original head motion sequences. The results also show that head motion modifies the emotional perception of the facial animation especially in the valence and activation domain. These results suggest that appropriate head motion not only significantly improves the naturalness of the animation but can also be used to enhance the emotional content of the animation to effectively engage the users

LLE 알고리즘을 사용한 얼굴 모션 데이터의 투영 및 실시간 표정제어

본 논문은 얼굴 모션 캡쳐 데이터를 재사용하여 실시간 표정 제어 및 표정 애니메이션을 생성하기 위한 방법론을 기술한다. 이 방법의 핵심요소는 얼굴 표정들을 정의할 수 있는 표정상태 표현법을 정하고, 이를 LLE 알고리즘에 적용하여 표정들을 적당한 공간에 분포시키는 방법론과, 이 공간을 사용하여 실시간 표정 애니메이션 생성 및 표정제어를 수행하기 위한 사용자 인터페이스 기법이다. 본 논문에서는 약 2400개의 얼굴 표정 프레임 데이터를 이용하여 공간을 생성하고, 애니메이터가 이 공간을 자유롭게 항해할 때, 항해경로 상에 위치한 얼굴 표정 프레임 데이터들이 연속적으로 선택되어 하나의 애니메이션이 생성되거나 표정제어가 가능하도록 하였다. 약 2400개의 얼굴 표정 프레임 데이터들을 직관적인 공간상에 분포하기 위해서는 얼굴 표정 프레임 데이터로부터 얼굴 표정상태를 표현할 필요가 있고, 이를 위해서는 임의의 두 마커 사이의 거리들로 구성된 거리행렬 벡터를 이용한다. 직관적인 공간에서의 데이터 배치는 얼굴 표정상태벡터들의 집합을 LLE 알고리즘에 적용하고, 이로부터 2차원 평면에 균일하게 분포하였다. 본 논문에서는 애니메이터로 하여금 사용자 인터페이스를 사용하여 실시간으로 표정 애니메이션을 생성하거나 표정제어를 수행하도록 하였으며, 그 결과를 평가한다. This paper describes methodology that enables animators to create the facial expression animations and to control the facial expressions in real-time by reusing motion capture datas. In order to achieve this, we fix a facial expression state expression method to express facial states based on facial motion data. In addition, by distributing facial expressions into intuitive space using LLE algorithm, it is possible to create the animations or to control the expressions in real-time from facial expression space using user interface. In this paper, approximately 2400 facial expression frames are used to generate facial expression space. In addition, by navigating facial expression space projected on the 2-dimensional plane, it is possible to create the animations or to control the expressions of 3-dimensional avatars in real-time by selecting a series of expressions from facial expression space. In order to distribute approximately 2400 facial expression data into intuitional space, there is need to represents the state of each expressions from facial expression frames. In order to achieve this, the distance matrix that presents the distances between pairs of feature points on the faces, is used. In order to distribute this datas, LLE algorithm is used for visualization in 2-dimensional plane. Animators are told to control facial expressions or to create animations when using the user interface of this system. This paper evaluates the results of the experiment.

Expressive Facial Animation Synthesis by Learning Speech Coarticulation and Expression Spaces

Synthesizing expressive facial animation is a very challenging topic within the graphics community. In this paper, we present an expressive facial animation synthesis system enabled by automated learning from facial motion capture data. Accurate 3D motions of the markers on the face of a human subject are captured while he/she recites a predesigned corpus, with specific spoken and visual expressions. We present a novel motion capture mining technique that "learns" speech coarticulation models for diphones and triphones from the recorded data. A Phoneme-Independent Expression Eigenspace (PIEES) that encloses the dynamic expression signals is constructed by motion signal processing (phoneme-based time-warping and subtraction) and Principal Component Analysis (PCA) reduction. New expressive facial animations are synthesized as follows: First, the learned coarticulation models are concatenated to synthesize neutral visual speech according to novel speech input, then a texture-synthesis-based approach is used to generate a novel dynamic expression signal from the PIEES model, and finally the synthesized expression signal is blended with the synthesized neutral visual speech to create the final expressive facial animation. Our experiments demonstrate that the system can effectively synthesize realistic expressive facial animation.

A DYNAMIC EMOTION REPRESENTATION MODEL WITHIN A FACIAL ANIMATION SYSTEM

This paper presents the Dynamic Emotion Representation (DER), and demonstrates how an instance of this model can be integrated into a facial animation system. The DER model has been implemented to enable users to create their own emotion representation. Developers can select which emotions they include and how these interact. The instance of the DER model described in this paper is composed of three layers, each representing states changing over different time scales: behavior activations, emotions and moods. The design of this DER is discussed with reference to emotion theories and to the needs of a facial animation system. The DER is used in our Emotionally Expressive Facial Animation System (EE-FAS) to produce emotional expressions, to select facial signals corresponding to communicative functions in relation to the emotional state of the agent and also in relation to the comparison between the emotional state and the intended meanings expressed through communicative functions.

Emotional face expression profiles supported by virtual human ontology

Expressive facial animation synthesis of human like characters has had many approaches with good results. MPEG-4 standard has functioned as the basis of many of those approaches. In this paper we w...

얼굴 표정의 자동 인식을 통한 PDA 상에서의 3차원 얼굴 애니메이션

In this paper, we present a facial expression recognition-synthesis system that recognizes 7 basic emotion information automatically and renders face with non-photorelistic style in PDA For the recognition of the facial expressions, first we need to detect the face area within the image acquired from the camera. Then, a normalization procedure is applied to it for geometrical and illumination corrections. To classify a facial expression, we have found that when Gabor wavelets is combined with enhanced Fisher model the best result comes out. In our case, the out put is the 7 emotional weighting. Such weighting information transmitted to the PDA via a mobile network, is used for non-photorealistic facial expression animation. To render a 3-D avatar which has unique facial character, we adopted the cartoon-like shading method. We found that facial expression animation using emotional curves is more effective in expressing the timing of an expression comparing to the linear interpolation method.

Mood swings: expressive speech animation

Motion capture-based facial animation has recently gained popularity in many applications, such as movies, video games, and human-computer interface designs. With the use of sophisticated facial motions from a human performer, animated characters are far more lively and convincing. However, editing motion data is difficult, limiting the potential of reusing the motion data for different tasks. To address this problem, statistical techniques have been applied to learn models of the facial motion in order to derive new motions based on the existing data. Most existing research focuses on audio-to-visual mapping and reordering of words, or on photo-realistically matching the synthesized face to the original performer. Little attention has been paid to modifying and controlling facial expression, or to mapping expressive motion onto other 3D characters.This article describes a method for creating expressive facial animation by extracting information from the expression axis of a speech performance. First, a statistical model for factoring the expression and visual speech is learned from video. This model can be used to analyze the facial expression of a new performance or modify the facial expressions of an existing performance. With the addition of this analysis of the facial expression, the facial motion can be more effectively retargeted to another 3D face model. The blendshape retargeting technique is extended to include subsets of morph targets that belong to different facial expression groups. The proportion of each subset included in a final animation is weighted according to the expression information. The resulting animation conveys much more emotion than if only the motion vectors were used for retargeting. Finally, since head motion is very important in adding liveness to facial animation, we introduces an audio-driven synthesis technique for generating new head motion.

A new physical model with multilayer architecture for facial expression animation using dynamic adaptive mesh

This paper presents a new physically-based 3D facial model based on anatomical knowledge which provides high fidelity for facial expression animation while optimizing the computation. Our facial model has a multilayer biomechanical structure, incorporating a physically-based approximation to facial skin tissue, a set of anatomically-motivated facial muscle actuators, and underlying skull structure. In contrast to existing mass-spring-damper (MSD) facial models, our dynamic skin model uses the nonlinear springs to directly simulate the nonlinear visco-elastic behavior of soft tissue and a new kind of edge repulsion spring is developed to prevent collapse of the skin model. Different types of muscle models have been developed to simulate distribution of the muscle force applied on the skin due to muscle contraction. The presence of the skull advantageously constrain the skin movements, resulting in more accurate facial deformation and also guides the interactive placement of facial muscles. The governing dynamics are computed using a local semi-implicit ODE solver. In the dynamic simulation, an adaptive refinement automatically adapts the local resolution at which potential inaccuracies are detected depending on local deformation. The method, in effect, ensures the required speedup by concentrating computational time only where needed while ensuring realistic behavior within a predefined error threshold. This mechanism allows more pleasing animation results to be produced at a reduced computational cost.

Sammon 매핑을 사용한 모션 데이터의 대화식 표정 애니메이션

본 논문은 다량의 고차원 얼굴 표정 모션 데이터를 2차원 공간에 분포시키고, 애니메이터가 이 공간을 항해하면서 원하는 표정들을 실시간 적으로 선택함으로써 얼굴 표정 애니메이션을 생성하는 방법을 기술한다. 본 논문에서는 약 2400여개의 얼굴 표정 프레임을 이용하여 표정공간을 구성하였다. 표정공간의 생성은 임의의 두 표정간의 최단거리의 결정으로 귀결된다. 표정공간은 다양체 공간으로서 이 공간내의 두 점간의 거리는 다음과 같이 근사적으로 표현한다. 임의의 마커간의 거리를 표시하는 거리행렬을 사용하여 각 표정의 상태를 표현하는 표정상태벡터를 정의한 후, 두 표정이 인접해 있으면, 이를 두 표정 간 최단거리(다양체 거리)에 대한 근사치로 간주한다. 그리하여 인접 표정들 간의 인접거리가 결정되면, 이틀 인접거리들을 연결하여 임의의 두 표정 상태간의 최단거리를 구하는데, 이를 위해 Floyd 알고리즘을 이용한다. 다차원 공간인 표정공간을 가시화하기 위해서는 Sammon 매핑을 이용하여 2차원 평면에 투영시켰다. 얼굴 애니메이션은 사용자 인터페이스를 사용하여 애니메이터들이 2차원 공간을 항해하면서 실시간으로 생성한다. This paper describes method to distribute much high-dimensional facial expression motion data to 2 dimensional space, and method to create facial expression animation by select expressions that want by realtime as animator navigates this space. In this paper composed expression space using about 2400 facial expression frames. The creation of facial space is ended by decision of shortest distance between any two expressions. The expression space as manifold space expresses approximately distance between two points as following. After define expression state vector that express state of each expression using distance matrix which represent distance between any markers, if two expression adjoin, regard this as approximate about shortest distance between two expressions. So, if adjacency distance is decided between adjacency expressions, connect these adjacency distances and yield shortest distance between any two expression states, use Floyd algorithm for this. To materialize expression space that is high-dimensional space, project on 2 dimensions using Sammon's Mapping. Facial animation create by realtime with animators navigating 2 dimensional space using user interface.

Current status and future needs in craniofacial imaging.

Imaging is a keystone in understanding and delivery of craniofacial health care. Recent developments in imaging have brought forth many diverse technologies and approaches. This review provides the current status of methods in craniofacial imaging and discusses future needs and directions. New developments in three-dimensional dental and skeletal imaging, as well as three-dimensional facial image acquisition and animation of jaw movement and facial expression are reviewed. Visualization and convergence of the data from these technologies for construction of patient-specific models is described. Insights on how these technologies and approaches could impact research, education as well as the future of craniofacial health care will be discussed.

HFSM: HIERARCHICAL FACIAL SHAPE MODELING ALGORITHM FOR REALISTIC FACIAL EXPRESSION ANIMATION

We propose a hierarchical 3D facial modeling technique for realistic facial expression animation from the anatomical specification. We analyze the real human face to construct the facial model with a hierarchical biomechanical structure, incorporating a physically-based approximation to facial skin tissue, a set of anatomically-motivated facial muscle actuators and underlying skull structure. The deformable skin model has multi-layer structure to approximate different types of soft tissue. It takes into account the nonlinear stress-strain relationship of the skin and the fact that soft tissue is almost incompressible. Different kinds of muscle models have been developed to simulate the distribution of the muscle force exerted to the skin due to muscle contraction. The 3D face model incorporates a skull structure which extends the scope of facial motion and facilitates facial muscle construction. The facial muscle construction is achieved by a muscle mapping approach which efficiently locates facial muscles at the anatomically correct positions between the skin and skull layers. To generate facial expressions, the resulting hierarchical facial model is animated by solving the governing dynamic equation. For computational efficiency, we use a localized, semi-implicit integration method in the numerical simulation. The dynamic facial animation algorithm runs at an interactive rate and synthesizes various realistic facial expressions.

Synthetic faces: Analysis and applications

AbstractFacial animation has been a topic of intensive research for more than three decades. Still, designing realistic facial animations remains to be a challenging task. Several models and tools have been developed so far to automate the design of faces and facial animations synchronized with speech, emotions, and gestures. In this article, we take a brief overview of the existing parameterized facial animation systems. We then turn our attention to facial expression analysis, which we believe is the key to improving realism in animated faces. We report the results of our research regarding the analysis of the facial motion capture data. We use an optical tracking system that extracts the 3D positions of markers attached at specific feature point locations. We capture the movements of these face markers for a talking person. We then form a vector space representation by using the principal component analysis of this data. We call this space “expression and viseme space.” As a result, we propose a new parameter space for sculpting facial expressions for synthetic faces. Such a representation not only offers insight into improving realism of animated faces, but also gives a new way of generating convincing speech animation and blending between several expressions. Expressive facial animation finds a variety of applications ranging from virtual environments to entertainment and games. With the advances in Internet technology, the development of online sales assistants, Web navigation aides and Web‐based interactive tutors is promising than ever before. We overview the recent advances in the field of facial animation on the Web, with a detailed look at the requirements for Web‐based facial animation systems and various applications. © 2003 Wiley Periodicals, Inc. Int J Imaging Syst Technol 13: 65–73, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.10043

Image-based animation of facial expressions

We present a novel technique for creating realistic facial animations given a small number of real images and a few parameters for the in-between images. This scheme can also be used for reconstructing facial movies where the parameters can be automatically extracted from the images. The in-between images are produced without ever generating a three-dimensional model of the face. Since facial motion due to expressions are not well defined mathematically our approach is based on utilizing image patterns in facial motion. These patterns were revealed by an empirical study which analyzed and compared image motion patterns in facial expressions. The major contribution of this work is showing how parameterized “ideal” motion templates can generate facial movies for different people and different expressions, where the parameters are extracted automatically from the image sequence. To test the quality of the algorithm, image sequences (one of which was taken from a TV news broadcast) were reconstructed, yielding movies hardly distinguishable from the originals.