Thesis (B.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1981. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Bibliography: 2 unnumbered leaves following text. / by John Carlos Correa. / B.S.

Thesis (M.S.V.S.)--Massachusetts Institute of Technology, Dept. of Architecture, 1982. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ROTCH. / Bibliography: leaves 111-116. / The human face is a highly significant visual display which we are able to remember and recognize easily despite the fact that we are exposed to thousands of faces which may be metrically very similar. caricature is a graphical coding of facial features which seeks to be more like the face than the face itself: selected information is exaggerated, noise is reduced, and the processes involved in recognition are exploited. After studying the methods of caricaturists, examining perceptual phenomena regarding individuating features, and surveying automatic and man-machine systems which represent and manipulate the face, some heuristics for caricature are defined . An algorithm is implemented to amplify the nuance of a human face in a computer- generated caricature. This is done by comparing the face to a norm and then distorting the face even further away from that norm . Issues of style, context and animation are discussed. The applications of the caricature generator in the areas of teleconferencing, games, and interactive graphic interfaces are explored. / by Susan Elise Brennan. / M.S.V.S.

A Research Report submitted in partial fulfilment of the requirement for the Degree of Masters of Arts in Digital Animation at the University of the Witwatersrand (School of Digital Arts) Johannesburg, South Africa / In recent years, the quest for capturing authentic emotion convincingly in computer generated (CG) characters to assist exceedingly complex narrative expressions in modern cinema has intensified. Conveying human emotion in a digital human-like character is widely accepted to be the most challenging and elusive task for even the most skilled animators. Contemporary filmmakers have increasingly looked to complex digital tools that essentially manipulate the visual design of cinema through innovative techniques to reach levels of undetectable integration of CG characters. In trying to assess how modern cinema is pursuing the realistic integration of CG human-like characters in digital film with frenetic interest despite the risk of box office failure associated with the uncanny valley, this report focuses on the progress of the advances in the technique of facial motion capture. The uncanny valley hypothesis, based on a theory by Sigmund Freud, was coined in 1970 by Japanese robotics professor, Masahiro Mori. Mori suggested that people are increasingly comfortable with robots the more human-like they appear, but only up to a point. At that turning point, when the robot becomes too human-like, it arouses feelings of repulsion. When movement is added to this equation, viewers’ sense of the uncanny is heightened when the movement is deemed to be unreal. Motion capture is the technique of mimicking and capturing realistic movement by utilising technology that enables the process of translating a live actor’s performance into a digital performance. By capturing and transferring the data collected from sensors placed on a body suit or tracked from a high definition video, computer artists are able to drive the movement of a corresponding CG character in a 3-Dimensional (3D) programme. The attention of this study is narrowed to the progress of the techniques developed during a prolific decade for facial motion capture in particular. Regardless of the conflicting discourse surrounding the use of motion capture technology, these phenomenal improvements have allowed filmmakers to overcome that aspect of the uncanny valley associated with detecting realistic movement and facial expression. The progress of facial motion capture is investigated through the lens of selected films released during the period of 2001 to 2012. The two case studies, The Curious Case of Benjamin Button (2008) and Avatar (2009) were chosen for their individual achievement and innovative techniques that introduced new methods of facial capture. Digital images are said to undermine the reality status of cinematic images by challenging the foundation of long held theories of cinematic realist theory. These theories rooted in the indexical basis of photography, have proved to be the origin of contemporary viewers' notion of cinematic realism. However, the relationship between advanced digital effects and modern cinematic realism has created a perceptual complexity that warrants closer scrutiny. In addressing the paradoxical effect that photo-real cinematic realism is having on the basic comprehension of realism in film, the history of the seminal claims made by recognized realist film theorists is briefly examined.

Reconstruire, synthétiser, analyser et réutiliser les formes dynamiques capturées depuis le monde en mouvement est un défi récent qui reste encore en suspens. Dans cette thèse, nous abordons le problème de l'extraction, l'acquisition et la réutilisation d'une paramétrisation non-rigide pour l'animation basée vidéo. L'objectif principal étant de préserver les propriétés globales et locales de la surface capturée sans squelette articulé, grâce à un nombre limité de paramètres contrôlables, flexibles et réutilisables. Pour résoudre ce problème, nous nous appuyons sur une réduction de dimensions détachée de la surface reposant sur le paradigme de la représentation par cage. En conséquence, nous démontrons la force d'un sous-espace de la forme d'une cage géométrique pour encoder des surfaces fortement non-rigides. / Reconstructing, synthesizing, analyzing to re-using dynamic shapes that are captured from the real-world in motion isa recent and outstanding challenge. Nowadays, highly-detailed animations of live-actor performances are increasinglyeasier to acquire and 3D Video has reached considerable attention in visual media production. In this thesis, we addressthe problem of extracting or acquiring and then reusing non-rigid parametrization for video-based animations. At firstsight, a crucial challenge is to reproduce plausible boneless deformations while preserving global and local capturedproperties of the surface with a limited number of controllable, flexible and reusable parameters. To solve this challenge,we directly rely on a skin-detached dimension reduction thanks to the well-known cage-based paradigm. Indeed, to thebest of our knowledge, this dissertation opens the field of cage-based performance capture. First, we achieve ScalableInverse Cage-based Modeling by transposing the inverse kinematics paradigm on surfaces. To do this, we introduce acage inversion process with user-specified screen-space constraints. Secondly, we convert non-rigid animated surfacesinto a sequence of estimated optimal cage parameters via a process of Cage-based Animation Conversion. Building onthis reskinning procedure, we also develop a well-formed Animation Cartoonization algorithm for multi-view data in termof cage-based surface exaggeration and video-based appearance stylization. Thirdly, motivated by the relaxation of priorknowledge on the data, we propose a promising unsupervised approach to perform Iterative Cage-based GeometricRegistration. This novel registration scheme deals with reconstructed target point clouds obtained from multi-view videorecording, in conjunction with a static and wrinkled template mesh. Above all, we demonstrate the strength of cage-basedsubspaces in order to reparametrize highly non-rigid dynamic surfaces, without the need of secondary deformations. Inaddition, we state and discuss conclusions and several limitations of our cage-based strategies applied to life-like dynamicsurfaces, captured for vision-oriented applications. Finally, a variety of potential directions and open suggestions for furtherwork are outlined.

Watermana is a concept, the title of this thesis and the title of the work produced in conjunction with this thesis. The word 'mana' loosely translates as a form of spiritual power. In the form of Water Mana, it specifically means spiritual empowerment of feelings or emotions. This work is closely entwined with the video 'Watermana'. The research documented here both leads to the work and arose from its process. It reflects finding connections with Celtic shamanistic practices, and utilizing them in a modern urban context. It also explores poetry, its relationship to shamanism, and its possible structural relationships to film. 'Watermana' is a twelve-minute video produced using three-dimensional computer modelling and animation and live video, edited and composited digitally. It is a representation of a shamanistic journey and an introduction to the shamanistic process. / Master of Arts (Hons)

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.

"December 2006" / Bibliography: leaves 299-333. / xi, 333 leaves : / Title page, contents and abstract only. The complete thesis in print form is available from the University Library. / Thesis (D.Ed.)--University of Adelaide, School of Education, 2007

Thesis (M.S.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Sciences, Computer Science Department, 2006. / Includes bibliographical references.

Thesis (Ph. D.)--Ohio State University, 2006. / Title from first page of PDF file. Includes bibliographical references (p. 131-139).

This thesis researches techniques for modelling static facial expressions, as well as the dynamics of continuous facial motion. We demonstrate how static and dynamic properties of facial expressions can be represented within a linear and nonlinear context, respectively. These two representations do not act in isolation, but are mutually reinforcing in conceding a cohesive framework for the analysis, animation, and manipulation of expressive faces. We derive a basis for the linear space of expressions through Principal Components Analysis (PCA). We introduce and formalize the notion of "expression manifolds", manifolds residing in PCA space that model motion dynamics for semantically similar expressions. We then integrate these manifolds into an animation workflow by performing Nonlinear Dimensionality Reduction (NLDR) on the expression manifolds. This operation yields expression maps that encode a wealth of information relating to complex facial dynamics, in a low dimensional space that is intuitive to navigate and efficient to manage.