Rozprawy doktorskie na temat „3D computer animation”

A project produced for Karlshamns AB. This project is a 3D-visualization for a industrial process that shows how to clean oil from a special raw material. In this case we want with the sheanuts help show how the nut harvests, carry and then clean to be used in quality products.
Industriell animation som visar en komplicerad process på ett enkelt och pedagogiskt sätt.
Detta är en reflektionsdel till en digital medieproduktion.

Much research has been done in creating non-photorealistic renderings of objects that mimic the look of hand-made drawings by traditional artists. This thesis extends work in this area by presenting an NPR hatching method that can be applied to 3D animated films to help them feel more hand drawn. In contrast to most other NPR methods, this method preserves the 3D lighting and effects of the film that make it interesting to watch. This process includes a procedural algorithm to create a hatching pattern that can be easily integrated into any film's pipeline that uses Renderman. In addition, we create a set of controls to adjust the hatching that are easy to use and allow our style to be applied to many different objects in many shots of a film in an efficient manner. To show the success of our method, we will discuss the implementation and results of applying it to an actual 3D animated short film.

Detta arbete undersöker huruvida vi kan uppfatta lögn och nervositet hos en avskalad virtuell karaktär. Utifrån forskning om beteendevetenskap, kroppsspråk och icke-verbala signaler har lögnsignaler och nervositetstecken animerats hos en avskalad virtuell karaktär. Dessa animationer visades utan audiella ledtrådar, såsom tal, för urvalsgrupper och en kvantitativ undersökning genomfördes för att besvara arbetets frågeställning. Undersökningens resultat gav emellertid inget konkret svar på frågeställningen. För att respondenterna skulle uppfatta lögnsignaler hos en avskalad virtuell karaktär krävdes att ett flertal aspekter togs i beaktning, exempelvis behövde lögnsignalerna vara tydliga och inte överskuggas av starkare känslor eller signaler. Nervositetstecken avlästes dock enkelt av respondenterna i undersökningen vilket kan betyda att en avskalad virtuell karaktär kan gestalta ett nervöst tillstånd utan audiella ledtrådar. Resultatet som undersökningen gav har ställts mot insamlad data och tidigare forskning för att diskutera undersökningens brister och lämpliga framtida justeringar för att åtgärda dessa. Slutligen har även möjligheter för framtida arbete diskuterats och spekulationer kring användningsområden för en liknande undersökning i ett branschperspektiv har genomförts.

This research assesses the skills and knowledge necessary for the creation of animation in the 3D computer medium. It responds to the argument that students of this new form of animation must learn to apply principles and theories of animation that had their genesis in the early years of traditional, hand-drawn animation (Kroyer, 2002). Many industry notables argue for the use of traditional animation principles in 3D computer animation. John Lasseter, executive vice president at Pixar studios in the United States, represents one such example. He states that 'These principles were developed to make animation, especially character animation, more realistic and entertaining. These principles can and should be applied to 3D computer animation' (Lasseter 1987). The importance of animation principles in all animation mediums is stressed by Oscar-winning traditional animator Gene Deitch. He states that 'Every animated film made today uses those same basic principles developed at the Walt Disney studios during the 1930s. They still apply, no matter which technology is used' (2001). This research report examines the validity of this argument and identifies the tools, principles, and procedures that professional 3D animators are using. Central to this research is the dynamic of the contemporary relevance of traditional animation as an aesthetic, craft and economic entity. Most importantly this research considers how that dynamic might translate into the teaching of 3D animation courses. It is claimed that the findings of this research benefits 3D animation teachers, students, and those who employ them. To conduct on-site research with professional animators, this study enlisted the participation of a small number of animation studios in south-east Queensland, Australia by ensuring the protection of their Intellectual Property. Close observation of their working practices was made and numerous secondary sources of information (3D animation tutorials, books, DVDs, software manuals etc.) examined in order to locate the tools, processes, and principles that CG animators engaged. The findings were applied and critically assessed by means of a practical project (a seven-minute 3D-animated film) which was created concurrently with the research. Recommendations were formulated as to the most useful tools, processes, and principles for the student of computer animation by way of a revision of the existing Queensland College of Art syllabus for teaching computing animation. What follows is an account of the development and context of the project, the research methods applied, and critical analyses of the findings. The research concludes that it is necessary and advantageous to apply traditional animation skills to 3D computer work.

This research assesses the skills and knowledge necessary for the creation of animation in the 3D computer medium. It responds to the argument that students of this new form of animation must learn to apply principles and theories of animation that had their genesis in the early years of traditional, hand-drawn animation (Kroyer, 2002). Many industry notables argue for the use of traditional animation principles in 3D computer animation. John Lasseter, executive vice president at Pixar studios in the United States, represents one such example. He states that 'These principles were developed to make animation, especially character animation, more realistic and entertaining. These principles can and should be applied to 3D computer animation' (Lasseter 1987). The importance of animation principles in all animation mediums is stressed by Oscar-winning traditional animator Gene Deitch. He states that 'Every animated film made today uses those same basic principles developed at the Walt Disney studios during the 1930s. They still apply, no matter which technology is used' (2001). This research report examines the validity of this argument and identifies the tools, principles, and procedures that professional 3D animators are using. Central to this research is the dynamic of the contemporary relevance of traditional animation as an aesthetic, craft and economic entity. Most importantly this research considers how that dynamic might translate into the teaching of 3D animation courses. It is claimed that the findings of this research benefits 3D animation teachers, students, and those who employ them. To conduct on-site research with professional animators, this study enlisted the participation of a small number of animation studios in south-east Queensland, Australia by ensuring the protection of their Intellectual Property. Close observation of their working practices was made and numerous secondary sources of information (3D animation tutorials, books, DVDs, software manuals etc.) examined in order to locate the tools, processes, and principles that CG animators engaged. The findings were applied and critically assessed by means of a practical project (a seven-minute 3D-animated film) which was created concurrently with the research. Recommendations were formulated as to the most useful tools, processes, and principles for the student of computer animation by way of a revision of the existing Queensland College of Art syllabus for teaching computing animation. What follows is an account of the development and context of the project, the research methods applied, and critical analyses of the findings. The research concludes that it is necessary and advantageous to apply traditional animation skills to 3D computer work.
Thesis (Professional Doctorate)
Doctor of Visual Arts (DVA)
Griffith Film School
Full Text

L'analyse du visage est un sujet très étudié dans de nombreux domaines : Interaction Homme Machine, sécurité, post-production cinématographique, jeux video. . . Cela comprend la détection, la reconnaissance, la reconstruction 3D, l'animation et l'analyse d'émotions. L'animation du visage a été la motivation principale durant toute la thèse. Nous nous intéressons à la plupart des domaines liés au visage : tout d'abord la reconstruction 3D et la modélisation de visage, avec un nouveau modèle de visage. Ensuite, nous introduisons des contraintes anthropométriques par champs de Markov pour la détection globale de points d'intérêts. Partant de contraintes anthropométriques, nous sommes capables d'estimer la pose 3D du visage à partir d'une seule image, et de l'étendre au suivi du visage. L'analyse d'émotion conclut notre travail : nous présentons une technique de modélisation d'expression définie comme une série temporelle et proposons de l'utiliser pour la prédiction d'émotions.

Att utveckla 3D-animeringar till dataspel är kostsamt eftersom det tar mycket tid och resurser för att uppnå den kvalitet som dagens spelare kräver. För att både spara arbetstid och göra det lättare för ovana animatörer att skapa animationer av tillräckligt hög kvalitet undersöker detta arbete hur ett verktyg för regelbaserad procedurell animering kan utformas, vad spelare anser om resultatet och vad utvecklare anser om både resultat och användning. För att testa detta skapades en artefakt (ett rymdspel) bestående av 3D-modeller och programmering (C# i Unity) av script, API, klasser och metoder. Arte­fakten animerar procedurellt utifrån algoritmer baserade på variabler. Utvärderingen av artefakten genomfördes med stöd av funktionsprotokoll, enkät och intervjuer. Slutsatsen är att regelbaserad procedurell animering är användbar för mekaniska delar utifrån synpunkter från dataspelsutvecklare och spelare. Framtida arbete kan bestå av en utökad undersökning med fler respondenter, tillförande av ett grafiskt gränssnitt, produktutveckling tillsammans med företag, skapande av fler verktyg och användade av AI.

As humans, our fascination with recreating images of ourselves began with parietal art many thousands of years ago, and has continued throughout the ages. However, we also now strive to create moving, thinking, believable, virtual humans, rather than focus entirely on static images. Moreover, computer generated humans are now integral to the digital world that encompasses us, yet 3D animation remains rife with challenges. The overarching objective of the thesis, therefore, is to systematically investigate and design a comprehensive computational model that leverages the effect of natural motion from the real-world to mediate enhanced 3D animation production. Thus natural motion is simulated to support user engagement, leveraged through real-time mapping, and for control of digital characters through enabling devices for markerless capture. Captured data is analysed offline to identify potential creative enhancements. As a result of the comprehensive investigation, contributions include an innovative animation framework to support real and virtual engagement within immersive environments. The novel approach simulates motion, through combining elements of real-time game technology with facets of behaviour simulation from Embodied Conversational Agents. Contributions are also proposed towards bridging the gap between realistic motion capture and authoring more stylised 3D cartoon animations. Shortcomings of transferring natural motion to exaggerated cartoon styled animation are systematically studied and a solution based on parametric motion curve optimization is proposed. Intelligent reasoning for validation of temporal sequencing of animation assets using a structured knowledge model, further contributes towards animation production through facilitating sharing animation planning across different domains. The computational model, thus embodies the concept that through systematic investigation of synergies and differences between natural motion and keyframe animation, the benefits of both can be fused together to target more efficient, yet believable, and even creative animation authoring.

Creation of 3D character animations is a complex and time-consuming process, and the character animator has to simultaneously consider a multitude of factors in order to create high quality expressive animation. The 12 Principles of Animation are traditionally considered as the main guidelines for creating high-grade character animation. The main focus of this research is the process of animating the 3D character’s body expression and the animator’s practice, particularly the Posing phase of the animation process. Although posing is not one of the 12 Principles of Animation, it can be considered as the superposition of a subset of those principles that the animator has to keep in mind, while creating key-poses for any specific movement of an animated character. Additional factors that should be considered by the animator during the Posing stage are body language and acting, along with the technicalities of the 3D character manipulation. Hence, Posing is regarded as an intricate process, making it rather challenging for the animator to avoid involuntary neglect of the large number of the aforementioned characteristics. This aspect of the 3D animation process is extremely important for the final creative result of the animation, in terms of character's expression, because if the key-poses are not well defined, the computer may not be able to generate sufficiently expressive animation. This would often result in work that may be subjectively judged as lower quality animations. This research developed the hypothesis that the key to create more expressive 3D character animation is located within Posing, in the Animation Blocking phase of the process. This thesis proposes that a systematisation of the Posing procedure taking advantage of certain Traditional Animation, Fine Arts and Acting concepts and their underlying rationale, can greatly benefit the animator. This thesis presents a new posing approach to 3D character animation, as a conceptual guideline which promotes the arrangement of the body parts into naturalistic patterns of expression. This is achieved by combining the concepts of Power Centre, Line of Action, Contrapposto and Serpentine Line in a systematic way, around a conceptual flow of force. These comprehensible high-level concepts make Posing and the animation process less complicated and more accessible. This allows animators of different levels to create more believable character body expressions in an easier and less time-consuming fashion, introducing better methods of more efficient workflows resulting in improved creative results over shorter periods of time. It is also demonstrated how the aforementioned concepts can be applied to a variety of animation styles – ranging from the more realistic to the more cartoonish ones. A prototype of a 3D Pose Tool was also developed, based on the rationale of the proposed approach, with the objective of being used as a visual guide for generation of new poses to be included in the case studies. Additionally, this tool produces visual evidence in the analysis of specific good and bad examples of character posing. This thesis, therefore, makes the argument that the proposed solution – whether accompanied with the complementary 3D Pose Tool or not – gives the animator the possibility to work the character body expression as a whole. Thus, avoiding stiffness and ensuring that the essential steps of posing are not neglected in the process. This was demonstrated with several cases, which give evidence of the usefulness of the approach as a contribution to create more expressive character animation and to produce it in a more efficient way.

3D Computer Graphics (CG) has become the dominant medium for modern animated feature films. It is widely understood that traditional principles of animation developed in the 1930s at the Walt Disney Studio remain applicable to this new medium and heavily influence the range of aesthetic motion styles in contemporary animation. Via a frame-by-frame textual analysis of four animated feature films, this thesis tests and confirms the validity of the principles of animation and expands upon them by reinterpreting the Disney principle of appeal as aesthetic harmony, which delineates the way in which character posing and transitions between poses contribute to the animated motion styles that animators work in today.

The aim of this study is to present a novel three dimensional (3D) facial animation method for morphing emotions and facial expressions from one face model to another. For this purpose, smooth and realistic face models were animated with thin plate splines (TPS). Neutral face models were animated and compared with the actual expressive face models. Neutral and expressive face models were obtained from subjects via a 3D face scanner. The face models were preprocessed for pose and size normalization. Then muscle and wrinkle control points were located to the source face with neutral expression according to the human anatomy. Facial Action Coding System (FACS) was used to determine the control points and the face regions in the underlying model. The final positions of the control points after a facial expression were received from the expressive scan data of the source face. Afterwards control points were transferred to the target face using the facial landmarks and TPS as the morphing function. Finally, the neutral target face was animated with control points by TPS. In order to visualize the method, face scans with expressions composed of a selected subset of action units found in Bosphorus Database were used. Five lower-face and three-upper face action units are simulated during this study. For experimental results, the facial expressions were created on the 3D neutral face scan data of a human subject and the synthetic faces were compared to the subject&rsquo
s actual 3D scan data with the same facial expressions taken from the dataset.

This creative project is a 3D animated short created in Softimage XSI. It tells the humoristic story of an old lady, Madame Sylvia, and a bird, who are trying to find their place in society and do not succeed. Madame Sylvia is an old surly woman who tries to be like the stereotyped image of the nice old lady feeding birds in a park. The bird on the contrary tries to differentiate himself from his fellow sparrows by acting differently. The humoristic denouement of the story shows that pretending to be someone else might not be the solution to fit into society. The piece lasts two and a half minutes. It has been put together in Encore on a DVD that presents special features including a gallery of illustrations and the storyboard drawn by the writer.
Department of Telecommunications

Mit Techniken der Computergraphik können bewegte drei-dimensionale Oberflächen mit höchsten visuellen Details generiert und dargestellt werden. Mittlerweile sind die Ergebnisse so gut, dass beispielsweise virtuelle menschliche Gesichter in Filmen und Videospielen kaum noch von realen zu unterscheiden sind. Auch in der Ergonomie werden immer genauere Mensch-Modelle und Simulationen verwendet, beispielsweise zur Validierung und Verbesserung von Textilien.

Synthesizing the realistic motion of a humanoid is a very sophisticated task, studied in different research areas. This work addresses the problem to synthetize realistic animations of 3D biped characters in a simulated environment, using genetic algorithms. Characters are represented as a structure of rigid bodies linked each other by 1DOF joints. Such joints are controlled by sinusoidal functions whose parameters are calculated by the genetic algorithm. Results, obtained by testing and comparing several different genetic operators, are presented. The system we have created allows the non-skilled user, to automatically create animations by setting only few key-poses of the characters.

Human beings have two perfectly aligned eyeballs working together sending three-dimensional images to the brain and providing accurate depth perception. I lack true stereoscopic vision. When I was five years old I had my second eye surgery and I remember lying blind and terrified for two days in the children's ward of Reid Memorial Hospital in Richmond, Indiana. I later learned that my eyes didn't align properly and for the rest of my life my right eye would "wander". Because of my condition, I was given a list of jobs that I could never perform, jobs where human lives are entrusted to skilled professionals wielding scalpels or landing jets. I could never be one of those people. Or so I was told. I've always had excellent vision, nearly 20/20 my whole life and I've never struggled academically. It's just that my eyes don't point in the same direction like everybody else. Those who know me best can see it, but I've learned ways to make it not so obvious. It's all I've ever known. But, in an ironic twist of fate, it's become clear that my lazy eye has taught me to "see" better than the average artist. Having spent the last five years of my life studying 3D Design and exploring the most advanced creative technology on the planet, I've created a series of computer-generated environments, objects and characters. This is my latest attempt to prove to the world that I can see just fine. I could've been a doctor or a pilot after all. In this paper I present to the world a digital friend manifested from my slightly skewed interpretation of the world. Rocky is part of my imagination brought to life in perfect three-dimensional clarity for the world to see. He's a symbolic representation of my childhood love for cartoons and science fiction. He is strong yet gentle, modest, intelligent and noble. And, he is fiercely protective of that scared and blind five-year old boy.

Futurist Sculpting is a collection of techniques for representing dynamic motion in a static three-dimensional model. These techniques allow digital artists to use animation as a new modeling tool. The idea of Futurist Sculpting is inspired by the works of the Italian Futurist artists and it aims to achieve the same goal as the one described by Umberto Boccioni, “to find a form that would be like a remembered motion, the product of time but permanent in space.” However, Futurist Sculpting extends Boccioni’s idea to the new medium of 3D animation and modeling, introducing the techniques of Motion Snapshot, Surface Differentiation, and Motion Elasticity. Motion Snapshot has evolved from the idea that multiple key poses captured at different stages of motion can successfully portray the idea of movement. Surface Differentiation was developed to remove redundancy of overlaping geometry introduced by snapshots occuring with high spatial frequency. Exploded Snapshot creates a geometric blur effect and extends application of Motion Snapshots to motion of deforming objects. The Motion Elasticity technique stretches the object to represent a partial volume through which it is moving. As a proof of concept all of the Futurist Sculpting techniques were implemented in Maya. The techniques should be viewed as a set of tools for the artists. The user can choose any one of them to apply to any animation, but he needs to understand their applications and limitations too.

Learning to read body language is something we do throughout our whole life. It is a complex non-verbal language that can express more than words. In this study we investigate the possibility to use only body language to portray emotions to the viewer. In a background of a game project we have used a character that has his face covered, therefore, facial expression is not visible during the online survey, which we used as a method for our investigation. As a foundation we have created four character animations to portray anger, frustration, exhaustion and hurt. To find the answer if it is possible to recognize those five emotions in the character animations survey, participants were obligated to name the emotion expressed on each of the video clips. The results of this study show that the characters body language could be sufficient to portray those five emotions. However, it was concluded that body language could be enough to represent the character's emotional state to the viewer; but by including facial expressions we could help to portray the emotion even further.

This thesis provides an example of creating a special cinematic style of Film Noir in computer-generated animation. The thesis is designed as a discussion of how a unique lighting style in computer graphics can be used to enhance visual storytelling for cinematic purposes. It provides digital filmmakers a beginning guide to deal with various lighting situations, and with cinematic lighting in 3D production.

Thesis (Ph. D.)--Computing, Georgia Institute of Technology, 2006.
Elizabeth Mynatt, Committee Member ; Janet Kolodner, Committee Member ; Amy Bruckman, Committee Chair ; Michael Eisenberg, Committee Member ; Mark Guzdial, Committee Member. Vita. Includes bibliographical references.

Background. Previous studies in the area of video generation using generative adversarial networks have shown limitations in perceived naturalism of the generated images. A previously proposed method of rendering and simulating clouds serves as the base for this thesis. Objectives. This thesis aims to propose a new method utilising machine learning in the context of generating 3D cloud animation in computer graphics. This aim is broken down into multiple objectives, with the primary ones being the following. The utilisation of a machine learning model includes the pre-processing of cloud images into cloud maps, training the model, as well as generating 2D cloud animations with it. 3D cloud animations are achieved by implementing the model into a pre-existing real-time cloud rendering framework. The performance of the implementation is measured and evaluated. Finally, a questionnaire is deployed and its results are analysed to evaluate the effectiveness of the proposed method. Methods. The image quality of the generated images is compared using an image quality assessment method which compares them to the data set used for training. Performance measurements are taken and compared between a base method reliant on Voronoi-noise and the proposed machine learning-based method. Finally, a questionnaire is deployed and then statistically analysed to evaluate the perceived naturalism of the base method and the proposed method. Results. The proposed method has a rendering time almost twice as long when compared to the base method when run in real-time. However, the results from the questionnaire showed that the proposed method achieves a higher level of perceived naturalism of the animation. Conclusions. The proposed method generates more natural animations than the base method at a higher cost in terms of time complexity.
Bakgrund. Tidigare studier inom videogeneration med generativa motverkande nätverk har visat begränsningar kring den upplevda naturligheten av de genererade bilderna. En tidigare föreslagen metod för rendering och simulering av moln fungerar som grund för denna uppsats. Syfte. Denna uppsats siktar på att föreslå en ny maskinlärningsbaserad metod till kontexten att generera 3D-molnanimationer inom datorgrafik. Syftet bryts ner i flera mål, av vilka de primära är som följande. Användandet av en maskinlärningsmodell inkluderar förbehandlingen av molnbilder till molnkartor, träningen av modellen samt genereringen av 2D-molnanimationer via modellen. 3D-molnanimationer uppnås genom att implementera modellen i ett förexisterande ramverk för realtidsbaserat molnrendering. Prestandan av implementationen mäts och evalueras. Slutligen distribueras ett frågeformulär vars resultat analyseras för att evaluera effektiviteten av den föreslagna metoden. Metod. Bildkvaliten av de genererade bilderna jämförs, med hjälp av en metod för bildkvalitetsevaluering, med datamängden som användes vid träningen. Prestandan mäts och jämförs mellan den gamla Voronoi-brusbaserade metoden och den föreslagna maskinlärningsbaserade metoden. Slutligen kommer ett frågeformulär skickas ut och därefter bli statistiskt analyserat för att evaluera den upplevda naturligheten mellan den gamla metoden och den föreslagna metoden. Resultat. Den föreslagna metoden har en renderingstid nästan dubbelt så hög som den gamla metoden när de kör i realtid. Dock visar resultatet från frågeformuläret att animationen i den föreslagna metoden uppnår en högre nivå av upplevd naturlighet. Slutsatser. Den föreslagna metoden genererar mer naturliga animationer än den gamla metoden till en höjning i tidskomplexitet

Title from PDF of title page (University of Missouri--Columbia, viewed on March 10, 2010). The entire thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file; a non-technical public abstract appears in the public.pdf file. Thesis advisor: Dr. Guilherme DeSouza. Vita. Includes bibliographical references.

What are some of the methods for rigging and animating a face in 3D and which method is preferable when and under which circumstances? In this report I will examine a few of the different methods available when rigging and animating a face in 3D. I will be working mainly with Autodesk 3D Studio Max so some knowledge with it is preferable to fully understand the process. At the end of the report I will look at the positive as well as negative aspects of each method as well as which method is preferable in what kind of production or with which assets.

 

To build muscles to enhance the animation of a 3D character takes more time and effort than the standard character rig. In some cases, the muscles will not be noticeable and therefore are unnecessary. This research tried to find the moments when the muscles did or did not make a difference. The new Maya Muscle System is also explored and the procedure to create muscles for a standard rig is explained. The test that was performed showed that the muscles are more noticeable in all cases.

 

La production de dessins animés 2D qui suit actuellement un schéma mis en place dans les années 1920 fait intervenir un très grand nombre de compétences humaines et de métiers différents. Par opposition à ce mode de travail traditionnel, la production de films de synthèse 3D, en exploitant les technologies et les outils les plus récents de modélisation et d'animation 3D, s'affranchit en bonne partie de cette composante artisanale et vient concurrencer l'industrie du dessin animé traditionnel en termes de temps et coûts de fabrication.
Les défis à relever par l'industrie du dessin animé 2D se posent donc en termes de :
1. Réutilisation des contenus selon le paradigme d'accès «Create once, render many»,
2. Facilité d'échange et de transmission des contenus ce qui nécessite de disposer d'un unique format de représentation,
3. Production efficace et économique des contenus requérant alors une animation automatisée par ordinateur.
Dans ce contexte compétitif, cette thèse, réalisée dans le cadre du projet industriel TOON financé par la société Quadraxis (www.quadraxis.com) et supporté par l'Agence Nationale de Valorisation de la Recherche (ANVAR), a pour objectif de contribuer au développement d'une plate-forme de reconstruction, déformation et animation de modèles 3D de visages pour les dessins animés 2D. Vecteurs de la parole et des expressions, les visages nécessitent en effet une attention particulière quant à leur modélisation et animation conforme aux souhaits des créateurs de dessins animés.
Un état de l'art des méthodes, outils et systèmes contribuant à la création de modèles 3D faciaux et à leur animation est présenté et discuté au regard des contraintes spécifiques qui régissent les règles de création des dessins animés 2D et la chaîne de fabrication traditionnelle.
Ayant identifié les verrous technologiques à lever, nos contributions ont porté sur :
 l'élaboration d'une méthode de conception de visages virtuels 3D à partir d'une part d'un modèle 3D de type seamless, adapté aux exigences d'animation sans rupture, et d'autre part d'un ensemble de dessins 2D représentant les caractéristiques faciales,
 la mise au point d'une procédure de création de poses clés, mettant en œuvre plusieurs méthodes de déformation non-rigide,
 la conception d'un module d'animation 3D compatible avec le standard MPEG-4/AFX.

Les développements réalisés, intégrés dans un premier prototype de la plate-forme FaceTOON, montrent un gain en temps de 20% sur l'ensemble de la chaîne de production tout en assurant une complète interopérabilité des applications via le standard MPEG-4.

En tant qu'une nouvelle alternative à la MoCap standard, la capture de surface 4D est motivée par la demande croissante des produits médiatiques de contenu 3D très réaliste. Ce type de données fournit une information complète et réelle de la forme, l'apparence et la cinématique de l'objet dynamique d'intérêt. On aborde dans cet ouvrage certaines taches liées à l'acquisition et l'exploitation de données 4D, obtenues à travers les vidéos multi-vues, avec un intérêt particulier aux formes humaines en mouvements. Parmi ces problèmes, certains ont déjà reçu beaucoup d'intérêt de la part des communautés de vision par ordinateur et d'infographie, mais plusieurs challenges restent ouverts à cet égard. En particulier, nous abordons la synthèse d'animation basée sur des exemples, la modélisation d'apparence et le transfert sémantique de mouvement.On introduit premièrement une méthode pour générer des animations en utilisant des séquences de maillages de mouvements élémentaires d'une forme donnée. De nouveaux mouvements satisfaisant des contraints hauts-niveaux sont construites en combinant et interpolant les trames des données observées. Notre méthode apporte une amélioration local au processus de la synthèse grâce à l'optimisation des transitions interpolées, ainsi qu'une amélioration globale avec une structure organisatrice optimale qu'on appelle le graph essentiel.On aborde en suite la construction de représentations efficaces de l'apparence de formes en mouvement observées à travers des vidéos multi-vue. On propose une représentation par sujet qui identifie la structure sous-jacente de l'information d'apparence relative à uneforme particulière. La représentation propre résultante représente les variabilités d'apparence dues au point de vue et au mouvement avec les textures propres, et celles dues aux imprécisions locales dans le modèle géométrique avec les déformations propres. Outre fournir des représentation compactes, ces décompositions permettent aussi l'interpolation et la complétion des apparences.Finalement, on s'intéresse au problème de transfert de mouvement entre deux modèles 4D capturés. Étant donné des ensembles d'apprentissages pour deux sujets avec des correspondances sémantiques éparses entre des poses clés, notre méthode est capable de transférer un nouveau mouvement capturé d'un sujet vers l'autre. Nous contribuons principalement un nouveau modèle de transfert basé sur l'interpolation non-linéaire de pose et de déplacement qui utilise les processus Gaussiens de régression
As a new alternative to standard motion capture, 4D surface capture is motivated by the increasing demand from media production for highly realistic 3D content.Such data provides real full shape, appearance and kinematic information of the dynamic object of interest. We address in this work some of the tasks related to the acquisition and the exploitation of 4D data, as obtained through multi-view videos, with an emphasis on corpus of moving subjects. Some of these problems have already received a great deal of interest from the graphics and vision communities, but a number of challenges remain open in this respect. We address namely example based animation synthesis, appearance modelling and semantic motion transfer.We first propose a method to generate animations using video-based mesh sequences of elementary movements of a shape. New motions that satisfy high-level user-specified constraints are built by recombining and interpolating the frames in the observed mesh sequences. Our method brings local improvement to the synthesis process through optimized interpolated transitions, and global improvement with an optimal organizing structure that we call the essential graph.We then address the problem of building efficient appearance representations of shapes observed from multiple viewpoints and in several movements. We propose a per subject representation that identifies the underlying manifold structure of the appearance information relative to a shape. The resulting Eigen representation encodes shape appearance variabilities due to viewpoint and illumination, with Eigen textures, and due to local inaccuracies in the geometric model, with Eigen warps. In addition to providing compact representations, such decompositions also allow for appearance interpolation and appearance completion.We finally address the problem of transferring motion between captured 4D models. Given 4D training sets for two subjects for which a sparse set of semantically corresponding key-poses are known, our method is able to transfer a newly captured motion from one subject to the other. The method contributes a new transfer model based on non-linear pose and displacement interpolation that builds on Gaussian process regression

Facial animation is an integral and increasing part of 3D games. This study investigates how the two most common methods of 3D facial animation compare to each other. The goal of this study is to summarize the situation and to provide animators and software developers with relevant recommendations. The two most utilized methods of facial animation; morph target animation and bone driven animation are examined with their strong and weak aspects presented. The investigation is based on literature analysis as well as a comparative case study approach which was used for comparing multiple formal and informal sources according to seven parameters such as: performance, production time, technical limitations, details and realism, ease of usability, cross platform compatibility and common combinations of systems. The strengths and weaknesses of the two methods of 3D facial animation are compared and discussed followed by a conclusion part which present recommendation to which is the preferable method to use under different circumstances. In some cases, the results are inconclusive due to a lack of data.  It is concluded that a combination of morph target and bone driven animation will give the most artistic control if time is not limited.

Popular fiction books describe rich visual environments that contain characters, objects, and behaviour. This research develops automated processes for converting text sourced from fiction books into animated virtual environments and multi-modal films. This involves the analysis of unrestricted natural language fiction to identify appropriate visual descriptions, and the interpretation of the identified descriptions for constructing animated 3D virtual environments. The goal of the text analysis stage is the creation of annotated fiction text, which identifies visual descriptions in a structured manner. A hierarchical rule-based learning system is created that induces patterns from example annotations provided by a human, and uses these for the creation of additional annotations. Patterns are expressed as tree structures that abstract the input text on different levels according to structural (token, sentence) and syntactic (parts-of-speech, syntactic function) categories. Patterns are generalized using pair-wise merging, where dissimilar sub-trees are replaced with wild-cards. The result is a small set of generalized patterns that are able to create correct annotations. A set of generalized patterns represents a model of an annotator's mental process regarding a particular annotation category. Annotated text is interpreted automatically for constructing detailed scene descriptions. This includes identifying which scenes to visualize, and identifying the contents and behaviour in each scene. Entity behaviour in a 3D virtual environment is formulated using time-based constraints that are automatically derived from annotations. Constraints are expressed as non-linear symbolic functions that restrict the trajectories of a pair of entities over a continuous interval of time. Solutions to these constraints specify precise behaviour. We create an innovative quantified constraint optimizer for locating sound solutions, which uses interval arithmetic for treating time and space as contiguous quantities. This optimization method uses a technique of constraint relaxation and tightening that allows solution approximations to be located where constraint systems are inconsistent (an ability not previously explored in interval-based quantified constraint solving). 3D virtual environments are populated by automatically selecting geometric models or procedural geometry-creation methods from a library. 3D models are animated according to trajectories derived from constraint solutions. The final animated film is sequenced using a range of modalities including animated 3D graphics, textual subtitles, audio narrations, and foleys. Hierarchical rule-based learning is evaluated over a range of annotation categories. Models are induced for different categories of annotation without modifying the core learning algorithms, and these models are shown to be applicable to different types of books. Models are induced automatically with accuracies ranging between 51.4% and 90.4%, depending on the category. We show that models are refined if further examples are provided, and this supports a boot-strapping process for training the learning mechanism. The task of interpreting annotated fiction text and populating 3D virtual environments is successfully automated using our described techniques. Detailed scene descriptions are created accurately, where between 83% and 96% of the automatically generated descriptions require no manual modification (depending on the type of description). The interval-based quantified constraint optimizer fully automates the behaviour specification process. Sample animated multi-modal 3D films are created using extracts from fiction books that are unrestricted in terms of complexity or subject matter (unlike existing text-to-graphics systems). These examples demonstrate that: behaviour is visualized that corresponds to the descriptions in the original text; appropriate geometry is selected (or created) for visualizing entities in each scene; sequences of scenes are created for a film-like presentation of the story; and that multiple modalities are combined to create a coherent multi-modal representation of the fiction text. This research demonstrates that visual descriptions in fiction text can be automatically identified, and that these descriptions can be converted into corresponding animated virtual environments. Unlike existing text-to-graphics systems, we describe techniques that function over unrestricted natural language text and perform the conversion process without the need for manually constructed repositories of world knowledge. This enables the rapid production of animated 3D virtual environments, allowing the human designer to focus on creative aspects.

Simulation modeling and visualization can substantially help in designing complex construction operations and in making optimal decisions where traditional methods prove ineffective or are unfeasible. However, there has been limited use of simulation in planning construction operations due to the unavailability of appropriate visual communication tools that can provide users with a more realistic and comprehensible feedback from simulation analyses. Visualizing simulated construction operations in 3D can significantly help in establishing the credibility of simulation models. In addition, 3D visualization can provide valuable insight into the subtleties of construction operations that are otherwise non-quantifiable and presentable. New software development technologies emerge at incredible rates that allow engineers and scientists to create novel, domain-specific applications. This study capitalized on a computer graphics technology based on the concept of the "Scene Graph" to design and implement a general-purpose 3D Visualization System that is Simulation and CAD-software independent. This system, the "Dynamic Construction Visualizer", enables realistic visualization of modeled construction operations and the resulting products in 3D and can be used in conjunction with a wide variety of simulation tools. This thesis describes the "Dynamic Construction Visualizer" as well as the "Scene Graph" architecture and the Frame Updating algorithms used in its design.
Master of Science

The design of autonomous agents capable of performing a given goal in a 3D domain continues to be a challenge for computer animated story generation systems. We present a novel prototype which consists of a 3D engine and a planner for a simple virtual world. We incorporate the 2D planner into the 3D engine to provide 3D animations. Based on the plan, the 3D world is created and the objects are positioned. Then the plan is linearized into simpler actions for object animation and rendered via the 3D engine. We use JINNI3D as the engine and WARPLAN-C as the planner for the above-mentioned prototype. The user can interact with the system using a simple natural language interface. The interface consists of a shallow parser, which is capable of identifying a set of predefined basic commands. The command given by the user is considered as the goal for the planner. The resulting plan is created and rendered in 3D. The overall system is comparable to a character based interactive story generation system except that it is limited to the predefined 3D environment.

This thesis proposes a new way to analyze facial expressions through 3D scanned faces of real-life people. The expression analysis is based on learning the facial motion vectors that are the differences between a neutral face and a face with an expression. There are several expression analysis based on real-life face database such as 2D image-based Cohn-Kanade AU-Coded Facial Expression Database and Binghamton University 3D Facial Expression Database. To handle large pose variations and increase the general understanding of facial behavior, 2D image-based expression database is not enough. The Binghamton University 3D Facial Expression Database is mainly used for facial expression recognition and it is difficult to compare, resolve, and extend the problems related detailed 3D facial expression analysis. Our work aims to find a new and an intuitively way of visualizing the detailed point by point movements of 3D face model for a facial expression. In our work, we have created our own 3D facial expression database on a detailed level, which each expression model has been processed to have the same structure to compare differences between different people for a given expression. The first step is to obtain same structured but individually shaped face models. All the head models are recreated by deforming a generic model to adapt a laser-scanned individualized face shape in both coarse level and fine level. We repeat this recreation method on different human subjects to establish a database. The second step is expression cloning. The motion vectors are obtained by subtracting two head models with/without expression. The extracted facial motion vectors are applied onto a different human subject’s neutral face. Facial expression cloning is proved to be robust and fast as well as easy to use. The last step is about analyzing the facial motion vectors obtained from the second step. First we transferred several human subjects’ expressions on a single human neutral face. Then the analysis is done to compare different expression pairs in two main regions: the whole face surface analysis and facial muscle analysis. Through our work where smiling has been chosen for the experiment, we find our approach to analysis through face scanning a good way to visualize how differently people move their facial muscles for the same expression. People smile in a similar manner moving their mouths and cheeks in similar orientations, but each person shows her/his own unique way of moving. The difference between individual smiles is the differences of movements they make.

The desktop publishing revolution of the 1980s is currently repeating itself in 3D, referred to as desktop manufacturing. Online services such as Shapeways have become available, making personalized manufacturing on cutting edge additive manufacturing (AM) technologies accessible to a broad audience. Affordable desktop printers will soon take over, enabling people to fabricate
Engineering and Applied Sciences

La production de dessins animés 2D, qui suit actuellement un schéma mis en place dans les années 1920, fait intervenir un très nombre de compétences humaines et de métiers différents. Par opposition à ce mode de travail traditionnel, la production de films de synthèse 3D, en exploitant les technologies et outils les plus récents de modélisation et d'animation 3D, s'affranchit pour une bonne part de cette composante artisanale et vient concurrencer l'industrie du dessin animé tradtionnel en termes de délais et de coûts de fabrication.

Les défis à relever par l'industrie du dessin animé 2D se formulent donc en termes de:

1. Réutilisation des contenus selon le paradigme Create once, render many,
2. Facilité d'échange et de transmission des contenus, ce qui nécessite de disposer d'un unique format de représentation,
3. Production efficace et économique des contenus, requérant une animation automatisée par ordinateur.

Dans ce contexte compétitif, ce travail de thèse, réalisé dans le cadre du projet industriel TOON financé par la société Quadraxis avec le support de l' Agence Nationale de Valorisation de la Recherche (Oséo-ANVAR), a pour objectif de contribuer au développement d'une plate-forme de reconstruction, déformation et animation de modèles 3D pour les dessins animés 2D.

Un état de l'art des méthodes et outils contribuant à la reconstruction de modèles 3D et à leur animation est présenté et discuté au regard des contraintes spécifiques des règles de création des dessins animés 2D et de la chaîne de fabrication traditionnelle. Ayant identifié les verrous technologiques à lever, nos contributions ont porté sur :

* l'élaboration d'une méthode de reconstruction de personnages virtuels 3D à partir de dessins 2D,
* la mise au point d'une procédure de reconstruction surfacique par NURBS dotée d'une capacité de déformation interactive 2D/3D,
* la conception d'un module de modélisation 3D pour surfaces maillées, compatible avec le standard d'animation MPEG-4/AFX.

Les développements réalisés, intégrés dans un prototype de la plate-forme TOON, montrent un gain en temps de 20% sur l'ensemble de la chaîne de production tout en garantissant une complète interopérabilité des applications via le standard MPEG-4.

Pour la téléconférence, on peut remplacer l'image des correspondants distants par des modèles 3D animés de leurs visages. En plus de taux de compression avantageux, cette approche offre les libertés du virtuel : on peut par exemple composer à l'écran l'impression d'un lieu unique, virtuel, où débattent les représentants 3D. Cette thèse présente un algorithme de rendu spécifique, applicable à des clones 3D photo-réalistes de visages. En restreignant les angles de vue autorisés, il permet un rendu simple et rapide, même avec des ordinateurs peu puissants ou sur des machines virtuelles. On propose aussi une architecture de régie automatique, reliée à des caméras virtuelles qui réagissent aux interventions des participants et en proposent une image synthétique. En alternant plusieurs vues (éventuellement partielles) de la scène, on autorise plus de participants simultanés, sans compromettre la qualité de l'image proposée ni l'intelligibilité du débat restitué. Automatique, cette approche libère l'utilisateur du système, qui peut se concentrer sur un débat rendu plus attractif, à la fois comme spectateur et comme participant. Cette thèse rend aussi compte de la réalisation d'un prototype de communication qui intègre les éléments précédents et permet de juger la qualité de la communication obtenue. À cette occasion, l'utilisation d'un environnement sonore qui intègre les interventions distantes et leur localisation (dans ou hors de l'image) est discutée, avec plusieurs expérimentations sur l'association entre l'image et le son spatialisé. Enfin, on introduit une solution hybride (3D et vidéo) pour animer les clones des visages. En incrustant à la surface d'un clone statique l'image des yeux, des sourcils et de la bouche vues par une caméra, on laisse aux spectateurs la responsabilité d'interpréter les expressions originales, dans toute leur dimension vidéo (forte résolution spatiale et temporelle). Un second prototype permet de juger de l'empathie visuelle.

This thesis is framed within the field of 3D Character Animation. Virtual characters are used in many Human Computer Interaction applications such as video games and serious games. Within these virtual worlds they move and act in similar ways to humans controlled by users through some form of interface or by artificial intelligence. This work addresses the challenges of developing smoother movements and more natural behaviors driving motions in real-time, intuitively, and accurately. The interaction between virtual characters and intelligent objects will also be explored. With these subjects researched the work will contribute to creating more responsive, expressive, and tangible virtual characters. The navigation within virtual worlds uses locomotion such as walking, running, etc. To achieve maximum realism, actors' movements are captured and used to animate virtual characters. This is the philosophy of motion graphs: a structure that embeds movements where the continuous motion stream is generated from concatenating motion pieces. However, locomotion synthesis, using motion graphs, involves a tradeoff between the number of possible transitions between different kinds of locomotion, and the quality of these, meaning smooth transition between poses. To overcome this drawback, we propose the method of progressive transitions using Body Part Motion Graphs (BPMGs). This method deals with partial movements, and generates specific, synchronized transitions for each body part (group of joints) within a window of time. Therefore, the connectivity within the system is not linked to the similarity between global poses allowing us to find more and better quality transition points while increasing the speed of response and execution of these transitions in contrast to standard motion graphs method. Secondly, beyond getting faster transitions and smoother movements, virtual characters also interact with each other and with users by speaking. This interaction requires the creation of appropriate gestures according to the voice that they reproduced. Gestures are the nonverbal language that accompanies voiced language. The credibility of virtual characters when speaking is linked to the naturalness of their movements in sync with the voice in speech and intonation. Consequently, we analyzed the relationship between gestures, speech, and the performed gestures according to that speech. We defined intensity indicators for both gestures (GSI, Gesture Strength Indicator) and speech (PSI, Pitch Strength Indicator). We studied the relationship in time and intensity of these cues in order to establish synchronicity and intensity rules. Later we adapted the mentioned rules to select the appropriate gestures to the speech input (tagged text from speech signal) in the Gesture Motion Graph (GMG). The evaluation of resulting animations shows the importance of relating the intensity of speech and gestures to generate believable animations beyond time synchronization. Subsequently, we present a system that leads automatic generation of gestures and facial animation from a speech signal: BodySpeech. This system also includes animation improvements such as: increased use of data input, more flexible time synchronization, and new features like editing style of output animations. In addition, facial animation also takes into account speech intonation. Finally, we have moved virtual characters from virtual environments to the physical world in order to explore their interaction possibilities with real objects. To this end, we present AvatARs, virtual characters that have tangible representation and are integrated into reality through augmented reality apps on mobile devices. Users choose a physical object to manipulate in order to control the animation. They can select and configure the animation, which serves as a support for the virtual character represented. Then, we explored the interaction of AvatARs with intelligent physical objects like the Pleo social robot. Pleo is used to assist hospitalized children in therapy or simply for playing. Despite its benefits, there is a lack of emotional relationship and interaction between the children and Pleo which makes children lose interest eventually. This is why we have created a mixed reality scenario where Vleo (AvatAR as Pleo, virtual element) and Pleo (real element) interact naturally. This scenario has been tested and the results conclude that AvatARs enhances children's motivation to play with Pleo, opening a new horizon in the interaction between virtual characters and robots.
Aquesta tesi s'emmarca dins del món de l'animació de personatges virtuals tridimensionals. Els personatges virtuals s'utilitzen en moltes aplicacions d'interacció home màquina, com els videojocs o els serious games, on es mouen i actuen de forma similar als humans dins de mons virtuals, i on són controlats pels usuaris per mitjà d'alguna interfície, o d'altra manera per sistemes intel·ligents. Reptes com aconseguir moviments fluids i comportament natural, controlar en temps real el moviment de manera intuitiva i precisa, i inclús explorar la interacció dels personatges virtuals amb elements físics intel·ligents; són els que es treballen a continuació amb l'objectiu de contribuir en la generació de personatges virtuals responsius, expressius i tangibles. La navegació dins dels mons virtuals fa ús de locomocions com caminar, córrer, etc. Per tal d'aconseguir el màxim de realisme, es capturen i reutilitzen moviments d'actors per animar els personatges virtuals. Així funcionen els motion graphs, una estructura que encapsula moviments i per mitjà de cerques dins d'aquesta, els concatena creant un flux continu. La síntesi de locomocions usant els motion graphs comporta un compromís entre el número de transicions entre les diferents locomocions, i la qualitat d'aquestes (similitud entre les postures a connectar). Per superar aquest inconvenient, proposem el mètode transicions progressives usant Body Part Motion Graphs (BPMGs). Aquest mètode tracta els moviments de manera parcial, i genera transicions específiques i sincronitzades per cada part del cos (grup d'articulacions) dins d'una finestra temporal. Per tant, la conectivitat del sistema no està lligada a la similitud de postures globals, permetent trobar més punts de transició i de més qualitat, i sobretot incrementant la rapidesa en resposta i execució de les transicions respecte als motion graphs estàndards. En segon lloc, més enllà d'aconseguir transicions ràpides i moviments fluids, els personatges virtuals també interaccionen entre ells i amb els usuaris parlant, creant la necessitat de generar moviments apropiats a la veu que reprodueixen. Els gestos formen part del llenguatge no verbal que acostuma a acompanyar a la veu. La credibilitat dels personatges virtuals parlants està lligada a la naturalitat dels seus moviments i a la concordança que aquests tenen amb la veu, sobretot amb l'entonació d'aquesta. Així doncs, hem realitzat l'anàlisi de la relació entre els gestos i la veu, i la conseqüent generació de gestos d'acord a la veu. S'han definit indicadors d'intensitat tant per gestos (GSI, Gesture Strength Indicator) com per la veu (PSI, Pitch Strength Indicator), i s'ha estudiat la relació entre la temporalitat i la intensitat de les dues senyals per establir unes normes de sincronia temporal i d'intensitat. Més endavant es presenta el Gesture Motion Graph (GMG), que selecciona gestos adients a la veu d'entrada (text anotat a partir de la senyal de veu) i les regles esmentades. L'avaluació de les animaciones resultants demostra la importància de relacionar la intensitat per generar animacions cre\"{ibles, més enllà de la sincronització temporal. Posteriorment, presentem un sistema de generació automàtica de gestos i animació facial a partir d'una senyal de veu: BodySpeech. Aquest sistema també inclou millores en l'animació, major reaprofitament de les dades d'entrada i sincronització més flexible, i noves funcionalitats com l'edició de l'estil les animacions de sortida. A més, l'animació facial també té en compte l'entonació de la veu. Finalment, s'han traslladat els personatges virtuals dels entorns virtuals al món físic per tal d'explorar les possibilitats d'interacció amb objectes reals. Per aquest fi, presentem els AvatARs, personatges virtuals que tenen representació tangible i que es visualitzen integrats en la realitat a través d'un dispositiu mòbil gràcies a la realitat augmentada. El control de l'animació es duu a terme per mitjà d'un objecte físic que l'usuari manipula, seleccionant i parametritzant les animacions, i que al mateix temps serveix com a suport per a la representació del personatge virtual. Posteriorment, s'ha explorat la interacció dels AvatARs amb objectes físics intel·ligents com el robot social Pleo. El Pleo s'utilitza per a assistir a nens hospitalitzats en teràpia o simplement per jugar. Tot i els seus beneficis, hi ha una manca de relació emocional i interacció entre els nens i el Pleo que amb el temps fa que els nens perdin l'interès en ell. Així doncs, hem creat un escenari d'interacció mixt on el Vleo (un AvatAR en forma de Pleo; element virtual) i el Pleo (element real) interactuen de manera natural. Aquest escenari s'ha testejat i els resultats conclouen que els AvatARs milloren la motivació per jugar amb el Pleo, obrint un nou horitzó en la interacció dels personatges virtuals amb robots.
Esta tesis se enmarca dentro del mundo de la animación de personajes virtuales tridimensionales. Los personajes virtuales se utilizan en muchas aplicaciones de interacción hombre máquina, como los videojuegos y los serious games, donde dentro de mundo virtuales se mueven y actúan de manera similar a los humanos, y son controlados por usuarios por mediante de alguna interfaz, o de otro modo, por sistemas inteligentes. Retos como conseguir movimientos fluidos y comportamiento natural, controlar en tiempo real el movimiento de manera intuitiva y precisa, y incluso explorar la interacción de los personajes virtuales con elementos físicos inteligentes; son los que se trabajan a continuación con el objetivo de contribuir en la generación de personajes virtuales responsivos, expresivos y tangibles. La navegación dentro de los mundos virtuales hace uso de locomociones como andar, correr, etc. Para conseguir el máximo realismo, se capturan y reutilizan movimientos de actores para animar los personajes virtuales. Así funcionan los motion graphs, una estructura que encapsula movimientos y que por mediante búsquedas en ella, los concatena creando un flujo contínuo. La síntesi de locomociones usando los motion graphs comporta un compromiso entre el número de transiciones entre las distintas locomociones, y la calidad de estas (similitud entre las posturas a conectar). Para superar este inconveniente, proponemos el método transiciones progresivas usando Body Part Motion Graphs (BPMGs). Este método trata los movimientos de manera parcial, y genera transiciones específicas y sincronizadas para cada parte del cuerpo (grupo de articulaciones) dentro de una ventana temporal. Por lo tanto, la conectividad del sistema no está vinculada a la similitud de posturas globales, permitiendo encontrar más puntos de transición y de más calidad, incrementando la rapidez en respuesta y ejecución de las transiciones respeto a los motion graphs estándards. En segundo lugar, más allá de conseguir transiciones rápidas y movimientos fluídos, los personajes virtuales también interaccionan entre ellos y con los usuarios hablando, creando la necesidad de generar movimientos apropiados a la voz que reproducen. Los gestos forman parte del lenguaje no verbal que acostumbra a acompañar a la voz. La credibilidad de los personajes virtuales parlantes está vinculada a la naturalidad de sus movimientos y a la concordancia que estos tienen con la voz, sobretodo con la entonación de esta. Así pues, hemos realizado el análisis de la relación entre los gestos y la voz, y la consecuente generación de gestos de acuerdo a la voz. Se han definido indicadores de intensidad tanto para gestos (GSI, Gesture Strength Indicator) como para la voz (PSI, Pitch Strength Indicator), y se ha estudiado la relación temporal y de intensidad para establecer unas reglas de sincronía temporal y de intensidad. Más adelante se presenta el Gesture Motion Graph (GMG), que selecciona gestos adientes a la voz de entrada (texto etiquetado a partir de la señal de voz) y las normas mencionadas. La evaluación de las animaciones resultantes demuestra la importancia de relacionar la intensidad para generar animaciones creíbles, más allá de la sincronización temporal. Posteriormente, presentamos un sistema de generación automática de gestos y animación facial a partir de una señal de voz: BodySpeech. Este sistema también incluye mejoras en la animación, como un mayor aprovechamiento de los datos de entrada y una sincronización más flexible, y nuevas funcionalidades como la edición del estilo de las animaciones de salida. Además, la animación facial también tiene en cuenta la entonación de la voz. Finalmente, se han trasladado los personajes virtuales de los entornos virtuales al mundo físico para explorar las posibilidades de interacción con objetos reales. Para este fin, presentamos los AvatARs, personajes virtuales que tienen representación tangible y que se visualizan integrados en la realidad a través de un dispositivo móvil gracias a la realidad aumentada. El control de la animación se lleva a cabo mediante un objeto físico que el usuario manipula, seleccionando y configurando las animaciones, y que a su vez sirve como soporte para la representación del personaje. Posteriormente, se ha explorado la interacción de los AvatARs con objetos físicos inteligentes como el robot Pleo. Pleo se utiliza para asistir a niños en terapia o simplemente para jugar. Todo y sus beneficios, hay una falta de relación emocional y interacción entre los niños y Pleo que con el tiempo hace que los niños pierdan el interés. Así pues, hemos creado un escenario de interacción mixto donde Vleo (AvatAR en forma de Pleo; virtual) y Pleo (real) interactúan de manera natural. Este escenario se ha testeado y los resultados concluyen que los AvatARs mejoran la motivación para jugar con Pleo, abriendo un nuevo horizonte en la interacción de los personajes virtuales con robots.

Den här uppsatsen handlar om skapandet av animerad 3D-film från idé till färdigt resultat. Även att på uppdrag av en extern beställare av filmen försöka tillgodose dennes önskemål och krav på bästa sätt. Med hjälp av en litteraturstudie och egna kunskaper diskuteras och beskrivs process och genomförande av animering och karaktärsdesign för att slutligen få fram en animerad film som är utformad enligt beställarens önskan.

This research aims to address one of the most challenging problems in the field of computer vision and computer graphics, that is, the reconstruction of smooth 3D human motions from monocular video containing unrestricted human movement. The objective is to propose novel methods which differ from the traditional kinematics/dynamics formulations and image based reconstruction methods to provide an alternative highly automated way for human animation from the most widely available source that records human movements and activities. Such methods should be relatively low-cost while avoiding many limitations that come up with current motion tracking equipment.Monocular images or video sequences are chosen as the source of the project, due to the fact that they are widely available through many ways, such as film making and even simple home videos. Most of such monocular images or video sequences are generally uncalibrated, i.e., the information on the camera from which these images are taken is not available. In addition, although 2D joint locations and body silhouettes can be extracted from the images, accuracy of such 2D feature extractions may not be satisfactory by current image processing techniques. Using such monocular image sequence as the input source, many techniques and algorithms are proposed in this research.A 3D skeletal human model based on human anatomy is constructed with angular constraints encoded in the joints according to the biomechanical and physiological knowledge. The model is simple and yet sufficient to simulate realistic human motions, while the computational expense is much lower when dealing with skeletal model than with any other human models. Relative lengths of every body part of the human model are adjusted to be consistent with the human subject in the source images before reconstruction. That is achieved by preciously acquired geometry information on the human subject of interest.A Motion Trend Analysis (MTA) method is proposed in this research to automatically reconstruct the 3D postures of the human subject of interest directly from the extracted 2D joint locations (with possible noise tolerance) at each image frame. This method utilized the information on previously reconstructed postures to assist positioning the joints of the human model to their proper 3D locations in the current frame. To ensure a reliable starting point in the reconstruction, manual adjustment may be required to improve the accuracy of the first three posture recoveries. 3D positional coherence of every joint between adjacent recovered postures can be obtained and maintained at a satisfactory level. Objective Function (OF) is defined to represent the 2D residuals between the extracted feature points and the corresponding features resulted from projecting the reconstructed human model to the projection plane. The OF also includes considerations of all 3D positional discrepancies at every joint between adjacent postures. By translating the pelvis joint and rotating each joint of the human model, a proper human posture that resembles the one represented in the monocular image can be created by searching for the minimum value of the OF. To balance 2D residuals and 3D discrepancies, weighting parameters (WP) determination routine was developed which is able to dynamically adjust the WP values for the 2D and 3D factors in an OF.3D acquisition of smooth and reasonable human motion is the main focus of this research. Such human motions are in high demand for applications involving virtual human movements. A Motion Level Control (MLC) algorithm was proposed to be integrated with the MTA system to further ensure the rotational coherence of the reconstruction results in 3D and improve the efficiency of the search process. Application of MLC can be divided into two modules: the relocation of the pelvis joint and the recoveries of the skeleton segments rotations. Based on MLC, the computational cost of the search procedure for the pelvis relocation and the skeleton adjustment in the human posture recovery will be significantly reduced. At the same time, rotational consistency of each body segment in the reconstructed motion can reach a satisfactory level. Experimental results from the proposed algorithm are highly satisfactory.This research also attempts to acquire smooth yet reasonable 3D human motions from the monocular images with body occlusion or based on extracted silhouettes. Existing techniques for recovering human postures usually require as input a human motion sequence where every body segment is visible at all time. Such requirement might not always be satisfied. The human motion to be reconstructed could contain occlusions where part or the body is obscured by other object in the scene or by another part of the human body itself. The input video could also be not clear enough to provide acceptable 2D joint extractions. This research extends the developed MTA and MLC and proposes novel methods to acquire the smooth and reasonable human postures under such circumstances. Experiments have produced very promising results.There are still many challenges ahead, especially on the preprocessing of the monocular images such as the accurate extraction of joint locations and fullyautomatic posture recoveries. Besides, the Objective Function and biomechanical constraints should be further studied to improve the general performance of the motion reconstruction system. Human motion reconstruction algorithm without accurate 2D inputs in terms of joint features or silhouettes should also be explored. The human motion reconstruction obtained from this research currently can handle 2D input with minor extraction errors. A more applicable system that can tolerate more input errors will be highly desirable and hence should attract some research attention. Technical issues to be explored and addressed in the future are identified and discussed in this thesis.

This study examined the differences and similarities in how animated 3D characters were perceived by individuals from Sweden and China. The study also attempted to examine how cultural aspects influenced the participants’ perceptions. Parts of the study were conducted through collaboration with the Chinese game company, Focus Games. A literature study focusing on body language and culture was conducted, as well as a game animation analysis featuring games from both western and East Asian developers. Based on the game analysis, 6 animations were created with movement qualities inspired by each of the cultures. The study was conducted through an online questionnaire, as well as shorter semi-structured interviews. The results show that there were certain similarities and differences in how participants perceived the animations, however the reason as to how cultural aspects influenced the responses was partially unanswered due to lack of data.

En animation de personnages 3D, la déformation de surface, ou skinning, est une étape cruciale. Son rôle est de déformer la représentation surfacique d'un personnage pour permettre son rendu dans une succession de poses spécifiées par un animateur. La plausibilité et la qualité visuelle du résultat dépendent directement de la méthode de skinning choisie. Sa rapidité d'exécution et sa simplicité d'utilisation sont également à prendre en compte pour rendre possible son usage interactif lors des sessions de production des artistes 3D. Les différentes méthodes de skinning actuelles se divisent en trois catégories. Les méthodes géométriques sont rapides et simples d'utilisation, mais leur résultats manquent de plausibilité. Les approches s'appuyant sur des exemples produisent des résultats réalistes, elles nécessitent en revanche une base de données d'exemples volumineuse, et le contrôle de leur résultat est fastidieux. Enfin, les algorithmes de simulation physique sont capables de modéliser les phénomènes dynamiques les plus complexes au prix d'un temps de calcul souvent prohibitif pour une utilisation interactive. Les travaux décrits dans cette thèse s'appuient sur Implicit Skinning, une méthode géométrique corrective utilisant une représentation implicite des surfaces, qui permet de résoudre de nombreux problèmes rencontrés avec les méthodes géométriques classiques, tout en gardant des performances permettant son usage interactif. La contribution principale de ces travaux est un modèle d'animation qui prend en compte les effets des muscles des personnages et de leur interactions avec d'autres éléments anatomiques, tout en bénéficiant des avantages apportés par Implicit Skinning. Les muscles sont représentés par une surface d'extrusion le long d'axes centraux. Les axes des muscles sont contrôlés par une méthode de simulation physique simplifiée. Cette représentation permet de modéliser les collisions des muscles entre eux et avec les os, d'introduire des effets dynamiques tels que rebonds et secousses, tout en garantissant la conservation du volume, afin de représenter le comportement réel des muscles. Ce modèle produit des déformations plus plausibles et dynamiques que les méthodes géométriques de l'état de l'art, tout en conservant des performances suffisantes pour permettre son usage dans une session d'édition interactive. Elle offre de plus aux infographistes un contrôle intuitif sur la forme des muscles pour que les déformations obtenues se conforment à leur vision artistique
Surface deformation, or skinning is a crucial step in 3D character animation. Its role is to deform the surface representation of a character to be rendered in the succession of poses specified by an animator. The quality and plausiblity of the displayed results directly depends on the properties of the skinning method. However, speed and simplicity are also important criteria to enable their use in interactive editing sessions. Current skinning methods can be divided in three categories. Geometric methods are fast and simple to use, but their results lack plausibility. Example-based approaches produce realistic results, yet they require a large database of examples while remaining tedious to edit. Finally, physical simulations can model the most complex dynamical phenomena, but at a very high computational cost, making their interactive use impractical. The work presented in this thesis are based on, Implicit Skinning, is a corrective geometric approach using implicit surfaces to solve many issues of standard geometric skinning methods, while remaining fast enough for interactive use. The main contribution of this work is an animation model that adds anatomical plausibility to a character by representing muscle deformations and their interactions with other anatomical features, while benefiting from the advantages of Implicit Skinning. Muscles are represented by an extrusion surface along a central axis. These axes are driven by a simplified physics simulation method, introducing dynamic effects, such as jiggling. The muscle model guarantees volume conservation, a property of real-life muscles. This model adds plausibility and dynamics lacking in state-of-the-art geometric methods at a moderate computational cost, which enables its interactive use. In addition, it offers intuitive shape control to animators, enabling them to match the results with their artistic vision

This  thesis  deals  with  production  of  three-dimensional  animated  model. Thesis is about model of billiard table and visualization of balls motion on its surface. Using simulation methods to solve the problem of balls motion is the goal of this work. This thesis contains summary of physical phenomena which describe the ball motion. There are also animation and simulation techniques which are used to create a model involved in this work. This thesis also deals with description of software, which can be used to create a three-dimensional model, animation and define user interaction. The second part of thesis describes how simulation program and visualization application was made. In the end, there are charts which describe ball behaviour involved in this work.