Abstract: Real time animation of human figures in virtual environments is an important problem in the context of computer games and virtual environments. Recently, the use of large collections of captured motion data has increased realism in character animation. However, assuming that the virtual environment is large and complex, the effort of capturing motion data in a physical environment and adapting them to an extended virtual environment is the bottleneck for achieving interactive character animation and control. We present a new technique for allowing our animated characters to navigate through a large virtual environment, which is constructed using a set of building blocks. The building blocks, called motion patches, can be arbitrarily assembled to create novel environments. Each patch is annotated with motion data, which informs what actions are available for animated characters within the block. The versatility and flexibility of our approach are demonstrated through examples in which multiple characters are animated and controlled at interactive rates in large, complex virtual environments.

Abstract: 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

Abstract: From the Publisher: [Digital] Lighting & Rendering teaches essential skills and concepts you can apply in any 3D rendering package, and includes tips and examples for Maya, LightWave 3D, Softimage XSI, 3D Studio MAX, Mental Ray, and other leading programs. But software is not the focus of this book - it's about what you can create." "Master Hollywood lighting techniques to produce professional results in any 3D package. Stage and frame your 3D animation for cinematic storytelling. Composite 3D models into real-world environments with perfectly matched illumination, shadows, and reflections. Render multilayer, multipass shots for professional visual effects production. Simulate the results of natural color temperatures, f-stops, and exposure times for photorealistic renderings. Understand the art and science behind raytracing, global illumination, radiosity, photon mapping, and caustics. Create rich texture maps that give flesh to your characters and local flavor to your 3D scenes.

Abstract: The purpose of this research is to investigate the process of mental imagery from a computational perspective, employing theories and resources from linguistics, natural language processing, and computer graphics about human language visualisation. This thesis presents our progress toward the automatic creation of 3D animation from natural language text. Lexical Visual Semantic Representation (LVSR) is proposed, which connects linguistic semantics to the visual semantics and is suitable for action execution (animation). We investigate visual semantics of verbs, and introduce the notion of visual valency which is used as a primary criterion to construct a visual semantic based ontology. The visual valency approach is a framework for modelling deeper semantics of verbs. Lexicon-based approaches used for word sense disambiguation are also discussed. The context and the senses of the ambiguous verb are analysed using hypernymy relations and word frequency information in WordNet and thematic roles in LCS (Lexical Conceptual Structure) database. The significance of this research is also related to an animation blending approach which combines precreated and dynamically generated animation facilities into a unified mechanism and an object-oriented object modelling approach for decentralising the control of animation engine. An intelligent storytelling system called CONFUCIUS, which visualizes single sentences into 3D animation, speech, and sound effects, has been implemented in Java and VRML. CONFUCIUS is an overall framework of language visualisation, using computer graphics techniques with NLP to achieve high-level animation generation. We conducted an evaluation experiment where subjects were asked to complete a questionnaire either rating agreement for the generated animation or selecting the closest text from four candidates which describes the animation best. The results show a low error rate of comprehension measures of animation (8.33%) and 3.82 average agreement score. We also evaluated the syntactic parsing by test-suite based diagnostic evaluation, and anaphora resolution and semantic analysis by corpus-based adequacy evaluation. CONFUCIUS gives promising results on word sense disambiguation (70% accuracy) with regard to the dataset it is tested on. Future work is suggested for extending the knowledge base and improving commonsense reasoning from lexicons to present more verb classes, extending language visualisation to discourse level, and applying physics, such as dynamics and kinematics, to 3D animation.

Abstract: At the turn of the millennium, science documentaries show a particular penchant for the abundant use of animated visuals, obviously facilitated by new digital television techniques such as videographic animation and computer animatronics. Analyzing two recent science documentary series (Walking with Dinosaurs and The Elegant Universe) this article discusses how scientists and television producers deploy digital animation to convince viewers of the plausibility of scientific theories in the fields of paleontology and physics. The question guiding these analyses is how the use of digital animation is grounded in ambiguous epistemological and ontological claims. Rather than lamenting the advancing pictorial effect and the demise of realism in ‘postmodern' science documentaries, it is argued that the multimedia mix of words, sounds and images both reflects and transforms our claims to knowledge. In fact, science documentaries do not illustrate but enablescientific claims; they visualize knowledge while substa...

Abstract: We present a novel approach to synthesizing accurate visible speech based on searching and concatenating optimal variable-length units in a large corpus of motion capture data. Based on a set of visual prototypes selected on a source face and a corresponding set designated for a target face, we propose a machine learning technique to automatically map the facial motions observed on the source face to the target face. In order to model the long distance coarticulation effects in visible speech, a large-scale corpus that covers the most common syllables in English was collected, annotated and analyzed. For any input text, a search algorithm to locate the optimal sequences of concatenated units for synthesis is described. A new algorithm to adapt lip motions from a generic 3D face model to a specific 3D face model is also proposed. A complete, end-to-end visible speech animation system is implemented based on the approach. This system is currently used in more than 60 kindergartens through third grade classrooms to teach students to read using a lifelike conversational animated agent. To evaluate the quality of the visible speech produced by the animation system, both subjective evaluation and objective evaluation are conducted. The evaluation results show that the proposed approach is accurate and powerful for visible speech synthesis.

Abstract: Many medical students have difficulty learning basic science, either because they find the material challenging to comprehend or because they believe it has limited clinical application. Computer-assisted instruction (CAI)--ie, computer animation--can clarify instruction by allowing students to visualize complex, dynamic processes in an interesting presentation. At West Virginia School of Osteopathic Medicine (WVSOM) in Lewisburg, a series of computer animations have been developed to present concepts in molecular and cellular biology. The author conducted an investigation to compare the efficacy of one representative computer animation with that of traditional textbook material. The subjects were 22 students who had been admitted to WVSOM but who had not yet begun classes. The experimental design of the study consisted of a prelesson test, a lesson, and a postlesson test. The lesson explained the process of deoxyribonucleic acid (DNA) replication using either a computer animation (n=12) or a chapter from a textbook (n=10). Lesson comprehension as measured by the tests was significantly higher for subjects who used the computer animation than for subjects who used the textbook (P<.01). Furthermore, reviewing the text after studying with the computer animation did not raise test scores, suggesting that the animation was sufficient for learning and the text was unnecessary. After the study, a majority of subjects indicated a preference for the animation over the text. These results demonstrate that CAI can be an effective tool for relating basic science to medical students by improving comprehension and eliciting interest in the lessons.

Abstract: Lifelike animation of object manipulation requires dynamic interaction between animated characters, objects, and their environment. These interactions can be animated automatically with physically based simulations but proper controls are needed to animate characters that move realistically and that accomplish tasks in spite of unexpected disturbances. This paper describes an efficient control algorithm that generates realistic animations by incorporating motion data into task execution. The end result is a versatile system for interactive animation of dynamic manipulation tasks such as lifting, catching, and throwing.

Abstract: In this paper, we detail an anatomically inspired, physically based model of the human torso designed for the visual simulation of respiration using a mixed system of rigid and deformable parts. Motion related to breath is a signature movement of the human body and an indicator for life but it has been largely overlooked by the graphics community. A novel composition of biological components is necessary to capture the key characteristics of breathing motion visible in the human trunk because the movement is generated fundamentally through the combination of both rigid bone and soft tissue. Our approach uses a simple physically based muscle element which is used throughout to drive the motion of the ribs and diaphragm as well as in other muscles, like those of the abdomen, to produce passive resistance. In addition, we describe an implementation of a straightforward method for preserving incompressible volume in deformable bodies to use in approximating the motion of the abdomen related to breath. Through the careful construction of this anatomically based torso, control for respiration becomes the generation of periodic contraction signals for a minimal set of two muscle groups. We show the flexibility of our approach through the animation of several breathing styles using our system.

Abstract: In an exemplary embodiment of the present invention a system, method and computer program product for creating at least a two dimensional or three dimensional (3D) datastream from a video with moving objects is disclosed. In an exemplary embodiment of the present invention, a method of creating animated objects in 2D or 3D from video, may include: receiving video information which may include a plurality of frames of digital video; receiving and adding metadata to the video information, the metadata relating to at least one object in motion in the digital video; and interpreting the metadata and the video information and generating a datastream in at least 2D. In an exemplary embodiment, 2D, 3D or more dimensional data may be used to provide an animation of the event of which the video was made. In an exemplary embodiment, a 2D or 3D gametracker, or play reviewer may be provided allowing animation of motion events captured in the video.

Abstract: Between the classic films of Walt Disney and the televised animation revolution of the 1960s was a critical decade in animation design. Amid Amidi, publisher of the influential "Animation Blast" magazine and Cartoon Brew blog charts the evolution of the modern style in animation, which abandoned the preferred "lifelike" anthopomorphic look for a more sophisticated and often abstract approach. In this way, animation design of the time has much in common with the modern movements in painting and graphic design. Gathering hundreds of rare and forgotten sketches, model boards, cels, and film stills, "Cartoon Modern" is a thoroughly researched, eye-popping, and delightful account of perhaps the most critical era of animation design.

Abstract: A common problem in virtual character computer animation concerns the preservation of the basic foot-floor constraint (or footplant), consisting in detecting it before enforcing it. This paper describes a system capable of generating motion while continuously preserving the footplants for a real-time, dynamically evolving context. This system introduces a constraint detection method that improves classical techniques by adaptively selecting threshold values according to motion type and quality. The footplants are then enforced using a numerical inverse kinematics solver. As opposed to previous approaches, we define the footplant by attaching to it two effectors whose position at the beginning of the constraint can be modified, in order to place the foot on the ground, for example. However, the corrected posture at the constraint beginning is needed before it starts to ensure smoothness between the unconstrained and constrained states. We, therefore, present a new approach based on motion anticipation, which computes animation postures in advance, according to time-evolving motion parameters, such as locomotion speed and type. We illustrate our on-line approach with continuously modified locomotion patterns, and demonstrate its ability to correct motion artifacts, such as foot sliding, to change the constraint position and to modify from a straight to a curved walk motion.

Abstract: In two experiments, we examined the persuasiveness of computer animation on juror decision making by comparing animation to diagrams in two mock trials—a plane crash case and a car accident case. The persuasiveness of the animation on verdicts was dependent on the case; in the plane crash case, participants rendered verdicts in favor of the side presenting the animation. In the car accident case, the animation had no effect on verdicts. The role of familiarity with the depicted scenario is discussed as a possible explanation for the differing impact of animation. Additionally, jurors’ expectations about the persuasiveness of animations were discrepant with the animations’ actual influence on jurors’ verdicts.

Abstract: In this paper, we formulate the problem of synthesizing facial animation from an input audio sequence as a dynamic audio-visual mapping. We propose that audio-visual mapping should be modeled with an input-output hidden Markov model, or IOHMM. An IOHMM is an HMM for which the output and transition probabilities are conditional on the input sequence. We train IOHMMs using the expectation-maximization(EM) algorithm with a novel architecture to explicitly model the relationship between transition probabilities and the input using neural networks. Given an input sequence, the output sequence is synthesized by the maximum likelihood estimation. Experimental results demonstrate that IOHMMs can generate natural and good-quality facial animation sequences from the input audio.

Abstract: Rendering computer animation frames is a very time consuming job. Using parallel computing on clusters and so-called render farms is a common solution to this problem. In this paper we describe how Grid computing can be used for computer animation rendering. We propose a framework for Grid rendering services, describe its implementation, and present the results and statistics. A loseless 3D compression algorithm was also devised to solve the existing problem of transferring gigabytes of scene representation files (Renderman (.rib) and mental images (.mi)). This compression algorithm has been filed for patent in Singapore.

Abstract: We present several practical improvements to the interactive evolution of 2D images, some of which are also applicable to more general genetic programming problems. We introduce tree alignments to improve the animation of evolved images when using genetic cross dissolves. The goal of these improvements is to strengthen the interactive evolution toolset and give the artist greater control and expressive power.

Abstract: Smooth transitions between rich media (e.g., animations of visual elements of a UI) are provided when a 'second' animation is started on a property of a visual element for which a 'first' animation is already running. When the second animation is started, an animation system causes a current value of the property that resulted from the running of the 'first' animation (i.e., snapshot) to be stored, terminates or releases the first animation, and then causes the second animation to run using the snapshot as the 'from' value of the property. Because the second animation 'begins' at exactly the point at which the first animation ended, the transition between the first and second animation is smooth. An animation storage object can be created for a property for which an animation has been triggered to store base values and snapshots of the property while being animated.

Abstract: In one aspect, the invention provides a graphical user interface for generating animation The graphical user interface comprises a search pane which includes a text box to input a search string to search for an animation effect; and a preview pane to display a result of the search in the form of at least one thumbnail, each representing an animation effect selected from a database of animation clips based on the input search string

Abstract: This article explains the usefulness and versatility of point primitives for graphics, visualization, rendering, modeling, and animation. The observations and findings are based on more than 8 years of research in point-based graphics and on many discussions with key researchers in this rapidly developing field. This article is intended to provide both a critical analysis and an inspiration for researchers and developers

Abstract: Meeting and lecture room technology is a burgeoning field. Such technology can provide real-time support for physically present participants, for online remote participation, or for offline access to meetings or lectures. Capturing relevant information from meetings or lectures is necessary to provide this kind of support. Multimedia presentation of this captured information requires a lot of attention. In this article, we focus on models and associated algorithms that steer the virtual presenter's presentation animations. In our approach, we generate the presentations from a script describing the synchronization of speech, gestures, and movements. The script has also a channel devoted to presentation sheets (slides) and sheet changes, which we assume are an essential part of the presentation. To present and explain information, this 3D humanoid presenter uses output channels such as speech and animation of posture, painting, and involuntary movements

Abstract: This paper presents a novel system framework for interactive, three-dimensional, stylized, abstract painterly rendering. In this framework, the input models are first represented using 3D point sets and then this point-based representation is used to build a multiresolution bounding sphere hierarchy. From the leaf to root nodes, spheres of various sizes are rendered into multiple-size strokes on the canvas. The proposed sphere hierarchy is developed using multiscale region segmentation. This segmentation task assembles spheres with similar attribute regularities into a meaningful region hierarchy. These attributes include colors, positions, and curvatures. This hierarchy is very useful in the following respects: 1) it ensures the screen-space stroke density, 2) controls different input model abstractions, 3) maintains region structures such as the edges/boundaries at different scales, and 4) renders models interactively. By choosing suitable abstractions, brush stroke, and lighting parameters, we can interactively generate various painterly styles. We also propose a novel scheme that reduces the popping effect in animation sequences. Many different stylized images can be generated using the proposed framework.

Abstract: Just add talent!Award-winning animator Tony White brings you the ultimate book for digital animation. Here you will find the classic knowledge of many legendary techniques revealed, paired with information relevant to today's capable, state-of-the-art technologies.White leaves nothing out. What contemporary digital animators most need to know can be found between this book's covers - from conceptions to creation and through the many stages of the production pipeline to distribution. This book is intended to serve as your one-stop how-to animation guide. Whether you're new to animation or a very experienced digital animator, here you'll find fundamentals, key classical techniques, and professional advice that will strengthen your work and well-roundedness as an animator.Speaking from experience, White presents time-honored secrets of professional animaton with a warm, masterly, and knowledgeable approach that has evolved from over 30 years as an award-winning animator/director.The book's enclosed downloadable resources presents classic moments from animation's history through White's personal homage to traditional drawn animation, "Endangered Species." Using movie clips and still images from the film, White shares the 'making of' journal of the film, detailing each step, with scene-by-scene descriptions, technique by technique. Look for the repetitive stress disorder guide on the downloadable resources, called, "Mega-hurts." Watch the many movie clips for insights into the versatility that a traditional, pencil-drawn approach to animaton can offer.

Abstract: True real-time animation of complex hairstyles on animated characters is the goal of this work, and the challenge is to build a mechanical model of the hairstyle which is sufficiently fast for real-time performance while preserving the particular behavior of the hair medium and maintaining sufficient versatility for simulating any kind of complex hairstyles. Rather than building a complex mechanical model directly related to the structure of the hair strands, we take advantage of a volume free-form deformation scheme. We detail the construction of an efficient lattice mechanical deformation model which represents the volume behavior of the hair strands. The lattice is deformed as a particle system using state-of-the-art numerical methods, and animates the hairs using quadratic B-spline interpolation. The hairstyle reacts to the body skin through collisions with a metaball-based approximation. The model is highly scalable and allows hairstyles of any complexity to be simulated in any rendering context with the appropriate trade off between accuracy and computation speed, fitting the need of level-of-detail optimization schemes.

Abstract: Motion capturing has become an important tool in fields such as sports sciences, biometrics, and particularly in computer animation, where large collections of motion material are accumulated in the production process In order to fully exploit motion databases for reuse and for the synthesis of new motions, one needs efficient retrieval and browsing methods to identify similar motions So far, only ad-hoc methods for content-based motion retrieval have been proposed, which lack efficiency and rely on quantitative, numerical similarity measures, making it difficult to identify logically related motions We propose an efficient motion retrieval system based on the query-by-example paradigm, which employs qualitative, geometric similarity measures This allows for intuitive and interactive browsing in a purely content-based fashion without relying on textual annotations We have incorporated this technology in a novel user interface facilitating query formulation as well as visualization and ranking of search results

Abstract: Animated shape transformations should be an intrinsic part of visual cyberworlds. However, quite often only limited animation of the polygon-based shapes can be found there, specifically when using the virtual reality modeling language (VRML) and its successor extensible 3D (X3D). This greatly limits the expressive power of visual cyberworlds and has motivated our research in this direction. In this paper, we present function-based extensions of VRML and X3D, which allow for time-dependent shape modeling on the web. Our shape modeling approach is based on the concurrent use of implicit, explicit and parametric functions defining geometry, appearance and their transformations through time. The functions are typed straight in VRML/X3D code as individual formulas and as function scripts. We have also developed a web enabled interactive software tool for modeling function-based VRML/X3D objects.

Abstract: In this paper, a robust 3D dance posture recognition system using two cameras is proposed. A pair of wide-baseline video cameras with approximately orthogonal looking directions is used to reduce pose recognition ambiguities. Silhouettes extracted from these two views are represented using Gaussian mixture models (GMM) and used as features for recognition. Relevance vector machine (RVM) is deployed for robust pose recognition. The proposed system is trained using synthesized silhouettes created using animation software and motion capture data. The experimental results on synthetic and real images illustrate that the proposed approach can recognize 3D postures effectively. In addition, the system is easy to set up without any need of precise camera calibration.

Abstract: We apply a neurobiological model of visual attention and gaze control to the automatic animation of a photorealistic virtual human head. The attention model simulates biological visual processing along the occipito-parietal pathway of the primate brain. The gaze control model is derived from motion capture of human subjects, using high-speed video-based eye and head tracking apparatus. Given an arbitrary video clip, the model predicts visual locations most likely to attract an observer's attention, and simulates the dynamics of eye and head movements towards these locations. Tested on 85 video clips including synthetic stimuli, video games, TV news, sports, and outdoor scenes, the model demonstrates a strong ability at saccading towards and tracking salient targets. The resulting autonomous virtual human animation is of photorealistic quality.

Abstract: During its almost forty years of existence, facial animation has seen a host of technologies being invented, then fading into obsolescence. The modelling and animation methods have mostly been dictated by the available hardware, which greatly evolved through the years. Many animation desiderata that have been considered dreams at the time are now reality while ever new frontiers are encountered and explored. This paper provides an overview of the historically used technologies and attempts to predict the future trends in the field of facial animation as it permeates the entertainment industry with its feature films and computer games; the broad field of visualisation in science, including medical science and forensic analysis; and the fast growing field of information and communication technology and human-computer interaction.