To see the other types of publications on this topic, follow the link: Computer generated images.
Dissertations / Theses on the topic 'Computer generated images'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Computer generated images.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Evans, Steven R. "The pixel generator : a VLSI device for computer generated images." Thesis, University of Sussex, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.332912.
Full text
2
Strassmann, Steven Henry. "Hairy brushes in computer-generated images." Thesis, Massachusetts Institute of Technology, 1986. http://hdl.handle.net/1721.1/78948.
Full text
3
Quan, Weize. "Detection of computer-generated images via deep learning." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALT076.
Full textAbstract:
Avec les progrès des outils logiciels d'édition et de génération d'images, il est devenu plus facile de falsifier le contenu des images ou de créer de nouvelles images, même pour les novices. Ces images générées, telles que l'image de rendu photoréaliste et l'image colorisée, ont un réalisme visuel de haute qualité et peuvent potentiellement menacer de nombreuses applications importantes. Par exemple, les services judiciaires doivent vérifier que les images ne sont pas produites par la technologie de rendu infographique, les images colorisées peuvent amener les systèmes de reconnaissance / surveillance à produire des décisions incorrectes, etc. Par conséquent, la détection d'images générées par ordinateur a attiré une large attention dans la communauté de recherche en sécurité de multimédia. Dans cette thèse, nous étudions l'identification de différents types d'images générées par ordinateur, y compris l'image de rendu et l'image coloriée. Nous nous intéressons à identifier si une image est acquise par une caméra ou générée par un programme informatique. L'objectif principal est de concevoir un détecteur efficace, qui a une précision de classification élevée et une bonne capacité de généralisation. Nous considérons la construction de jeux de données, l'architecture du réseau de neurones profond, la méthode d'entraînement, la visualisation et la compréhension, pour les problèmes d'investigation légale des images considérés. Nos principales contributions sont : (1) une méthode de détection d'image colorisée basée sur l'insertion d'échantillons négatifs, (2) une méthode d'amélioration de la généralisation pour la détection d'image colorisée, (3) une méthode d'identification d'image naturelle et d'image de rendu basée sur le réseau neuronal convolutif, et (4) une méthode d'identification d'image de rendu basée sur l'amélioration de la diversité des caractéristiques et des échantillons contradictoiresWith the advances of image editing and generation software tools, it has become easier to tamper with the content of images or create new images, even for novices. These generated images, such as computer graphics (CG) image and colorized image (CI), have high-quality visual realism, and potentially throw huge threats to many important scenarios. For instance, the judicial departments need to verify that pictures are not produced by computer graphics rendering technology, colorized images can cause recognition/monitoring systems to produce incorrect decisions, and so on. Therefore, the detection of computer-generated images has attracted widespread attention in the multimedia security research community. In this thesis, we study the identification of different computer-generated images including CG image and CI, namely, identifying whether an image is acquired by a camera or generated by a computer program. The main objective is to design an efficient detector, which has high classification accuracy and good generalization capability. Specifically, we consider dataset construction, network architecture, training methodology, visualization and understanding, for the considered forensic problems. The main contributions are: (1) a colorized image detection method based on negative sample insertion, (2) a generalization method for colorized image detection, (3) a method for the identification of natural image (NI) and CG image based on CNN (Convolutional Neural Network), and (4) a CG image identification method based on the enhancement of feature diversity and adversarial samples
4
Bassanino, May Nahab. "The perception of computer generated architectural images." Thesis, University of Liverpool, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.367240.
Full text
5
Beale, Gareth. "Representing Roman statuary using computer generated images." Thesis, University of Southampton, 2013. https://eprints.soton.ac.uk/375493/.
Full textAbstract:
This thesis explores the potential of computer graphics as a means of producing hypothetical visual reconstructions of a painted statue of a young woman discovered at Herculaneum in 2006 (inv. 4433/87021). The visualisations incorporate accurate representation of experimentally derived data using physically accurate rendering techniques. The statue is reconstructed according to a range of different hypotheses and is visualised within a selection of architectural contexts. The work presented here constitutes both a technical and theoretical innovation for archaeological research. The methodology describes the implementation of physically accurate computer graphical simulation as a tool for the interpretation, visualisation and hypothetical reconstruction of Roman sculpture. These developments are underpinned by a theoretical re-assessment of the value of computationally generated images and computational image making processes to archaeological practice.
6
Cartwright, Paul. "Realisation of computer generated integral three dimensional images." Thesis, De Montfort University, 2000. http://hdl.handle.net/2086/13289.
Full text
7
Payne, Doug. "Simulating perceived 3D images replayed by computer generated holograms." Thesis, Heriot-Watt University, 2004. http://hdl.handle.net/10399/355.
Full text
8
Rosenzweig, Elizabeth. "A personal color proofing system for computer generated images." Thesis, Massachusetts Institute of Technology, 1985. http://hdl.handle.net/1721.1/77304.
Full textAbstract:
Thesis (M.S.V.S.)--Massachusetts Institute of Technology, Dept. of Architecture, 1985.MICROFICHE COPY AVAILABLE IN ARCHIVES AND ROTCH.
Includes bibliographical references (leaves 71-73).
Just as the invention of photography challenged the world's visual literacy at the turn of the century, so has computer graphics begun to reshape visual communication. Although still in its infancy, recently developed tools for visual communication have made computer graphics and electronic imaging accessible to a much larger number of artists and other professionals. The use of these systems has emphasized a new need for an automatic color image proofing system combining text and images in variable size. Such a system would ease the distribution of and accessibility to digital images with high quality and low cost. This thesis describes the Color Proofer, a system that has been designed to meet these needs. This system includes a software package that performs basic image processing functions similar to basic darkroom manipulations, designed for color hardcopy. It also includes a system for creating halftone dot fonts to aid in the production of high quality color proofs. A typesetter capable of producing magazine quality color images and text is an integral component of the Color Proofer. The Color Proofer is designed for photographers and graphic designers who want high quality proofs of computer generated images.
by Elizabeth Rosenzweig.
M.S.V.S.
9
Youssef, Osama Hassan. "Acceleration techniques for photo realistic computer generated integral images." Thesis, De Montfort University, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.699807.
Full text
10
Oglesby, Corliss Deionn. "The New Frontier of Advertising: Computer-Generated Images as Influencers." UNF Digital Commons, 2019. https://digitalcommons.unf.edu/etd/861.
Full textAbstract:
The use of computer-generated images as influencers of consumer opinions and behavior is an emerging advertising strategy. This research investigates the advantages and disadvantages of using computer-generated images (CGI) as influencers of human behavior from the perspective of promoting a brand. The power of electronic word of mouth (social media) and how it is incorporated in computer-generated images used as influencers is discussed as a major factor in consumer decision making. The social media account content of computer-generated images was analyzed by conducting a frame analysis to discern how computer-generated images are portrayed on social media. A frame analysis of 577 social media posts was used to develop a framework for future social media strategies for computer-generated images. CGIs be portrayed as transparent, engaging, and as a socialite. Best practices for using computer-generated images were identified by conducting an interview with a representative of a brand that has collaborated with an influential computer-generated image. Innovation, listening to the consumer voice, and creative control should be prioritized in this growing field of CGIs and CGI partnerships.
11
Obert, Juraj. "REAL-TIME CINEMATIC DESIGN OF VISUAL ASPECTS IN COMPUTER-GENERATED IMAGES." Doctoral diss., University of Central Florida, 2010. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/4282.
Full textAbstract:
Creation of visually-pleasing images has always been one of the main goals of computer graphics. Two important components are necessary to achieve this goal --- artists who design visual aspects of an image (such as materials or lighting) and sophisticated algorithms that render the image. Traditionally, rendering has been of greater interest to researchers, while the design part has always been deemed as secondary. This has led to many inefficiencies, as artists, in order to create a stunning image, are often forced to resort to the traditional, creativity-baring, pipelines consisting of repeated rendering and parameter tweaking. Our work shifts the attention away from the rendering problem and focuses on the design. We propose to combine non-physical editing with real-time feedback and provide artists with efficient ways of designing complex visual aspects such as global illumination or all-frequency shadows. We conform to existing pipelines by inserting our editing components into existing stages, hereby making editing of visual aspects an inherent part of the design process. Many of the examples showed in this work have been, until now, extremely hard to achieve. The non-physical aspect of our work enables artists to express themselves in more creative ways, not limited by the physical parameters of current renderers. Real-time feedback allows artists to immediately see the effects of applied modifications and compatibility with existing workflows enables easy integration of our algorithms into production pipelines.Ph.D.
School of Electrical Engineering and Computer Science
Engineering and Computer Science
Computer Science PhD
12
Napleton, Steven. "The technological and aesthetic impact of computer-generated images on the Hollywood cinema." Thesis, University of East London, 2000. http://roar.uel.ac.uk/1296/.
Full textAbstract:
The cinema, as originally an analogue apparatus of representation, has a particularly complex and contradictory relationship to the incursion of new digital practices and potentialities. This thesis examines this relationship through a study of the impact of computer-generated images (CGI) on the Hollywood mode of production, and on its visual and narrative filmic codes. Computer animation is unquestionably a technology of digital simulation, and its initial presence is necessarily based on an aesthetics of simulation, visually separating, and diegetically demarcating, the digital image as virtual and artfficial. Consequently, most previous accounts of CGI have focused predominantly on films depicting cyberspace and VR, such as Tron and The Lawnmower Man, within the parameters of debates on special effects, the generic conventions of science fiction, and postmodern concerns with virtuality and simulation. In the early 1 990s, however, technological innovations facilitated the transition to an aesthetics of photorealism, emphasising the seamless compositing and integration of CGI characters, objects and environments with live-action. The thesis argues that the this shill is fundamental in establishing the commercial and aesthetic credibility of CGI as a production tool, and it is closely examined through a case study of Jurassic Park. The processes by which the first organic, photorealistic CG characters were created are analysed, with particular reference to the role of procedural and hand methods of computer animation in constructing a new virtual aesthetics. The integration of CGI as a production tool is also related to the diegetic presence of information technologies as narrative devices, and the extra-textual commercial and professional discourses through which CGI is explicated and celebrated. The thesis argues that the cinema is able to exploit the potential of digital methods, whilst simultaneously displaying a fundamental anxiety over the status of its own representational codes. Finally, strategies of visibility and virtuality in computer animation are further examined in the context of the emerging digital mode of production in Hollywood, and of the high concept film's role in multimedia marketing and distribution strategies
13
Ericson, Anton. "Object Recognition Using Digitally Generated Images as Training Data." Thesis, Uppsala universitet, Bildanalys och människa-datorinteraktion, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-200158.
Full textAbstract:
Object recognition is a much studied computer vision problem, where the task is to find a given object in an image. This Master Thesis aims at doing a MATLAB implementation of an object recognition algorithm that finds three kinds of objects in images: electrical outlets, light switches and wall mounted air-conditioning controls. Visually, these three objects are quite similar and the aim is to be able to locate these objects in an image, as well as being able to distinguish them from one another. The object recognition was accomplished using Histogram of Oriented Gradients (HOG). During the training phase, the program was trained with images of the objects to be located, as well as reference images which did not contain the objects. A Support Vector Machine (SVM) was used in the classification phase. The performance was measured for two different setups, one where the training data consisted of photos and one where the training data consisted of digitally generated images created using a 3D modeling software, in addition to the photos. The results show that using digitally generated images as training images didn’t improve the accuracy in this case. The reason for this is probably that there is too little intraclass variability in the gradients in digitally generated images, they’re too synthetic in a sense, which makes them poor at reflecting reality for this specific approach. The result might have been different if a higher number of digitally generated images had been used.
14
Goss, Keith Michael. "Multi-dimensional polygon-based rendering for motion blur and depth of field." Thesis, Brunel University, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.294033.
Full text
15
Enström, Olof. "Authentication Using Deep Learning on User Generated Mouse Movement Images." Thesis, Luleå tekniska universitet, Institutionen för system- och rymdteknik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-74203.
Full textAbstract:
Continuous authentication using behavioral biometrics can provide an additional layer of protection against online account hijacking and fraud. Mouse dynamics classification is the concept of determining the authenticity of a user through the use of machine learning algorithms on mouse movement data. This thesis investigates the viability of state of the art deep learning technologies in mouse dynamics classification by designing convolutional neural network classifiers taking mouse movement images as input. For purposes of comparison, classifiers using the random forest algorithm and engineered features inspired by related works are implemented and tested on the same data set as the neural network classifier. A technique for lowering bias toward the on-screen location of mouse movement images is introduced, although its effectiveness is questionable and requires further research to thoroughly investigate. This technique was named 'centering', and is used for the deep learning-based classification methods alongside images not using the technique. The neural network classifiers yielded single action classification accuracies of 66% for centering, and 78% for non-centering. The random forest classifiers achieved the average accuracy of 79% for single action classification, which is very close to the results of other studies using similar methods. In addition to single action classification, a set based classification is made. This is the method most suitable for implementation in an actual authentication system as the accuracy is much higher. The neural network and random forest classifiers have different strengths. The neural network is proficient at classifying mouse actions that are of similar appearance in terms of length, location, and curvature. The random forest classifiers seem to be more consistent in these regards, although the accuracy deteriorates for especially long actions. As the different classification methods in this study have different strengths and weaknesses, a composite classification experiment was made where the output was determined by the least ambiguous output of the two models. This composite classification had an accuracy of 83%, meaning it outperformed both the individual models.
16
Barr, Christopher. "Knee kinematics of total knee replacement patients : pre and post operative analysis using computer generated images." Thesis, University of Strathclyde, 2011. http://oleg.lib.strath.ac.uk:80/R/?func=dbin-jump-full&object_id=24363.
Full textAbstract:
Introduction: Osteoarthritis (OA) is one of the leading causes of disability, and the knee is the most commonly affected joint in the body. The last resort for treatment of knee OA is Total Knee Replacement (TKR) surgery. Despite numerous advances in prosthetic design, patients do not reach normal function after surgery. Current surgical decisions are made on 2D radiographs and patient interviews. Aims: The aim of this study was to compare knee kinematics pre and post TKR surgery using computer animated images of patient specific models under every day conditions. Methods: 7 subjects were recruited for the study. Subjects underwent 3D gait analysis during 4 every day activities, and medical imaging of the knee joint pre and one month post surgery. A 3D model was created from each of the scans, and the kinematic gait analysis data was used to animate the images. Results: Improvements were seen in range of motion in all 4 activities 1 year post surgery. The preoperative 3D images provide detailed information on the anatomy of the osteoarthritic knee. The postoperative images demonstrate potential future problems associated with the implant. Although not accurate enough to be of clinical use, the animated data can provide a valuable insight into what conditions cause damage to both the osteoarthritic and prosthetic knee joint. As the animated data does not require specialist training to view, the images can be utilised across the fields of health professionals and manufacturing in the assessment and treatment of patients pre and post knee replacement surgery. Future improvements in the collection and processing of data may yield clinically useful data. Conclusion: Although not yet of clinical use, the potential application of 3D animations of the knee joint pre and post surgery is widespread.
17
Cooper, C., and n/a. "Space subdivision and distributed databases in a multiprocessor raytracer." University of Canberra. Information Sciences & Engineering, 1991. http://erl.canberra.edu.au./public/adt-AUC20060629.145540.
Full textAbstract:
This thesis deals with computer generated images.
The thesis begins with an overview of a generalised
computer graphics system, including a brief survey of typical
methods for generating photorealistic images. One such
technique, ray tracing, is used as the basis for the work
which follows. The overview section concludes with a
statement of the aim which is to:
Investigate the effective use of available processing
power and effective utilisation of available memory by
implementing a ray tracing programme which uses space
subdivision, multiple processors and a distributed
world model database.
The problem formulation section describes the ray
tracing principle and then introduces the main areas of study.
The INMOS Transputer (a building block for concurrent
systems) is used to implement the multiple process ray tracer.
Space subdivision is achieved by repeated and regular
subdivision of a world cube (which contains the scene to be
ray traced) into named cubes, called octrees. The subdivision
algorithm continues to subdivide space until no octree
contains more than a specified number of objects, or until the
practical limit of space subdivision is reached.
The objects in the world model database are distributed
in a round robin manner to the ray trace processes. During
execution of the ray trace programme, information about each
object is passed between processes by a message mechanism.
The concurrent code for the transputer processes, written
in OCCAM 2, was developed using timing diagrams and signal
flow diagrams derived by analogy from digital electronics.
Structure diagrams, modified to be consistent with OCCAM 2
processes, were derived from the timing diagrams and signal
flow diagrams. These were used as a basis for the coding.
The results show that space subdivision is an effective
use of processor power because the number of trial
intersections of rays with objects is dramatically reduced.
In addition, distribution of the world model database avoids
duplication of the database in the memory of each process and
hence better utilisation of available memory is achieved.
The programmes are supported by a menu driven interface
(running on a PC AT) which enables the user to control the
ray trace processes running on the transputer board housed in
the PC.
18
Welker, Cécile. "La fabrique des "nouvelles images" : l’émergence des images de synthèse en France dans la création audiovisuelle (1968-1989)." Thesis, Sorbonne Paris Cité, 2015. http://www.theses.fr/2015USPCA116/document.
Full textAbstract:
Entre la première thèse en informatique graphique (soutenue en 1968) et la première publicité entièrement synthétique diffusée à la télévision (en 1983), les images de synthèse se transforment en “nouvelles images”. Il ne s’agit pas d’évaluer ces prétendues images nouvelles en fonction de leurs qualités distinctives de rupture ou de continuité que l’expression a tendance à appeler, mais d’étudier leur mode de production et de représentation afin de déterminer ce qu’elles montrent des techniques employées, et les imaginaires que ces dernières véhiculent au moment d’émergence de l’image numérique, comme autant de propositions créatives mais aussi d’enjeux idéologiques. Étudiées d’un point de vue technique puis esthétique, grâce à l’étude croisée de témoignages, de littérature grise, et de l’analyse formelle des films, ces productions donnent à voir un processus de réappropriation du médium, avant et après l’image. Si elle définit une histoire « officielle » des images de synthèse en France, en replaçant aussi précisément que possible les productions dans leur environnement technique, politique et culturel, cette thèse a finalement mis en évidence les temps des images de synthèse en tant que produit innovant, depuis leurs lieux de fabrication jusqu’à leurs lieux de légitimation. Ses conclusions mettent en jeu les différentes circulations locales des hommes, des outils et des images, au moment où la politique culturelle de 1981 favorise la jonction art-ordinateur, et l’indiscipline des créationsBetween the first PhD in computer graphics (defended in 1968) and the first entirely synthetic advertisement broadcast on television (1983), computer-generated images became “new images”. The aim is not to assess these so-called new images according to their distinctive qualities of rupture or continuity, as the expression would suggest, but rather to study their mode of production and representation in order to determine what they show from the techniques employed, and the imaginative worlds that they convey at the time of the emergence of digital images, like so many creative suggestions but also ideological issues. Studied first from a technical, then from an aesthetic point of view, thanks to the cross-study of testimonies, grey literature and a formal analysis of the movies, these productions show a process of recovery of the medium, before and after the image. This PhD not only defines an “official” history of computer-generated images in France, replacing as precisely as possible the productions in their technical, political and cultural environment, but it also reveals when computer-generated images are innovating products, from their places of fabrication to their places of legitimacy. The conclusions question the different local circulations of people, tools and images, at a time when the cultural policies of the year 1981 promotes the bond between art and computer, and the indiscipline of creations
19
Diffner, Fredrik, and Hovig Manjikian. "Training a Neural Network using Synthetically Generated Data." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-280334.
Full textAbstract:
A major challenge in training machine learning models is the gathering and labeling of a sufficiently large training data set. A common solution is the use of synthetically generated data set to expand or replace a real data set. This paper examines the performance of a machine learning model trained on synthetic data set versus the same model trained on real data. This approach was applied to the problem of character recognition using a machine learning model that implements convolutional neural networks. A synthetic data set of 1’240’000 images and two real data sets, Char74k and ICDAR 2003, were used. The result was that the model trained on the synthetic data set achieved an accuracy that was about 50% better than the accuracy of the same model trained on the real data set.Vid utvecklandet av maskininlärningsmodeller kan avsaknaden av ett tillräckligt stort dataset för träning utgöra ett problem. En vanlig lösning är att använda syntetiskt genererad data för att antingen utöka eller helt ersätta ett dataset med verklig data. Denna uppsats undersöker prestationen av en maskininlärningsmodell tränad på syntetisk data jämfört med samma modell tränad på verklig data. Detta applicerades på problemet att använda ett konvolutionärt neuralt nätverk för att tyda tecken i bilder från ”naturliga” miljöer. Ett syntetiskt dataset bestående av 1’240’000 samt två stycken dataset med tecken från bilder, Char74K och ICDAR2003, användes. Resultatet visar att en modell tränad på det syntetiska datasetet presterade ca 50% bättre än samma modell tränad på Char74K.
20
Lundberg, Annika. "Web designers, don’t be afraid to use low-quality images in e-retail, unless you want to impress users : Purchase intent and attitudes on product listing pages with varying product image quality." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-178217.
Full textAbstract:
Internet usage is increasing every year, and so do the different online activities on the internet. Online shopping is one of the most popular activities on the internet and is continuing to grow. This study investigated if visual information influences consumer behaviour on e-retail websites when shown together with non-imagery information. The study also looks at whether or not the visual information that is being presented is a factor for consumers behaviour, and if the quality of the image matters in purchase intent. Another point of view in this study was whether or not imagery information in e-retail would increase the consumer attitude towards the design and if the type of visual information mattered. A significant difference was found in purchase intent for products having imagery information, regardless of the quality. Attitudes towards e-retail designs with high-quality product images were also found to be significantly more positive over both no- and low-quality images. The findings of this study fills the gap whether or not visual stimuli influence consumers when displayed to products without visual stimuli. The type of product imagery information being displayed is also a factor for consumer enjoyment. High-quality visual information is perceived better compared to designs with low-quality and non-imagery product information.
21
Scott, T. D. "Adaptive network rendering in computer generated imagery." Thesis, Queen's University Belfast, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.390861.
Full text
22
Evemy, Jeffrey Dennis. "Real-time computer generated imagery using stream processing techniques." Thesis, University of Southampton, 1989. https://eprints.soton.ac.uk/411148/.
Full text
23
Stewart, Marilyn Galvin. "The computer-generated image : an analysis for art education pedagogy /." The Ohio State University, 1988. http://rave.ohiolink.edu/etdc/view?acc_num=osu1487595712158337.
Full text
24
Graham, Athelia. "The Effects of Homography on Computer-generated High Frequency Word Lists." Diss., CLICK HERE for online access, 2008. http://contentdm.lib.byu.edu/ETD/image/etd2692.pdf.
Full text
25
Galvão, E?ika César. "Towards a framework for critically understanding computer generated imagery /." The Ohio State University, 1995. http://rave.ohiolink.edu/etdc/view?acc_num=osu1487867541731077.
Full text
26
Buckley, Edward. "Computer-generated holograms for real-time image display and sensor applications." Thesis, University of Cambridge, 2007. https://www.repository.cam.ac.uk/handle/1810/284064.
Full textAbstract:
Presenting visual information holographically would have a number of significant advantages over conventional video projection techniques, not least extremely high efficiency and the potential for miniaturisation. However, until now, two-dimensional projection using binary phase computer-generated holograms has been affected by critical limitations imposed both by the computational complexity of the hologram-generated algorithms required, and by the poor quality of images produced by the binary holograms they generate. To address these twin deficiencies, a novel technique and methodology for hologram generation – optimised to a new psychometrically determined perceptual measure of image quality – is presented. Such an approach is demonstrated to be realistic in commercially available hardware, thus bringing a practical real-time holographic video implementation within reach. A further application of this technology outside the field of information display is demonstrated by a new class of sensors which combine high-quality image formation, with the efficiency of phase modulation and the flexibility of CGH technology, to form a precision measurement device which provides visual feedback without the use of electronics.
27
Jukes, Alexander P. "3-D computer generated animation and the material plane : an investigation of the material qualities of 3-D computer generated animation and relations to space and form." Thesis, Royal College of Art, 2017. http://researchonline.rca.ac.uk/2845/.
Full textAbstract:
This research considers the production and presentation of 3-D CGI animation where the intention is to explore the potential of this mode of practice as material. Through a practical and theoretical study, this research project outlines the proposal that within the context of 3-D CGI animation there exists a property that can be regarded as unique, or deemed as an essential quality, which in turn can be defined as material. The research refers directly to work developed by Structural/Materialist filmmakers and artists working in the 1960s and 1970s whose investigation into process and materiality acts as a method and potential framework for exploringapproaches and processes within 3-D CGI animation. The project asks the following questions: 1. Is it possible through a practical exploration to establish distinctiveness for 3-D CGI animation? 2. Can theoretical research in relation to media studies, film studies, specifically Structural/Materialist film assist to support and shape project development? 3. Can the practical work associated with the project and theoretical undertaking converge to support a basis for determining an individual characteristic for 3-D CGI animation? Hypothesis My hypothesis in relation to the expected findings and outcomes for the project can be distilled to form two strands: 1. That 3-D CGI is definable as a unique mode of production and can be classified as distinct from other digital modes of image production. That the result of the research will point towards a conceptualisation for 3-D CGI where as a process it has the capacity and the influence to be considered as a unique, discreet mode of production. That the qualities and the self-styled artefacts that emerge from the digital mass can be determined as definable products linked to a specific process.
28
Follain, Éric. "Le centre monumental romain d'Appolonia d'Illyrie : images de synthèse et restitutions archéologiques." Thesis, Lyon 2, 2012. http://www.theses.fr/2012LYO20005.
Full textAbstract:
Colonie grecque, Apollonia d’Illyrie (Albanie), a connu à l’époque romaine des phases de construction et d’aménagement importantes. En témoigne le centre monumental qui a fait l’objet de fouilles et de dégagements sous la direction du français Léon Rey au début du XXe siècle. Après la seconde guerre mondiale, les équipes albanaises ont poursuivi les recherches archéologiques et ont réalisé les restaurations et les présentations actuelles. Le centre monumental est organisé autour de deux édifices principaux, l’odéon et le monument des agonothètes. Ces lieux d’assemblée attestent du caractère public de ce secteur de la ville comme le fait un arc de triomphe légèrement postérieur. Des boutiques témoignent d’une fonction commerciale annexe. L’aspect religieux est illustré par un temple ionique, entouré d’un portique, associé à un bâtiment nommé usuellement "prytanée", et par un petit sanctuaire. Enfin, un édifice de plan carré peut être soit une bibliothèque soit un Augusteum. Après l’analyse des vestiges accessibles et de la documentation, une approche des fonctions des différents monuments et les renvois aux éléments comparatifs des hypothèses de restitutions sont proposées puis transposées en images de synthèse. Elles sont ensuite assemblées en une vision globale du centre monumental romain, dans son état du début du IIIe siècle ap. J.-C. Dans l’attente de l’achèvement des recherches sur l’agora, localisée à quelques centaines de mètres, cet ensemble pourrait être un complexe architectural dédié au culte impérial dont l’importance aurait attiré, dans le courant du IIe siècle, le bouleuterion que prudemment on désigne encore comme "monument des agonothètes"During the Roman period, “Apollonia of Illyria”, a greek settlement in Albania, knew several phases of construction and development. This is demonstrated by the study of the monumental center which was the object of excavations supervised by a French archaeologist Léon Rey at the beginning of the XXth century. After World War II, Albanian teams pursued the researches. They realized the restorations and the current presentations. The monumental center is organized around two main buildings, the Odeon and the “monument of Agonothetes”. These meeting places give evidence of the public character of this part of the city, just like the existence of a triumphal arch built later on. Shops also prove the commercial function of this place. Then, the religious function is illustrated by an ionic temple surrounded by a portico associated with a building named “prytaneum’ and by a small sanctuary. Finally, a square building is either a library or an “augusteum”. After an analysis of the visible vestiges and documentation, a report on the functions of the various monuments and a presentation of the comparative elements, the hypothesis of reconstructions will be proposed and transposed into computer-generated images. They will be assembled in a global vision of the roman monumental center at the beginning of the third century. Researches concerning the agora, localized a few hundred meters further, are not achieved yet but this place could be an architectural complex dedicated to imperial cult. During the second century, its importance could have attracted the bouleuterion that remains, for the moment, named as “monument of Agonothetes”
Kolonia greke e Apolonisë së Ilirisë, në Shqipëri, ka njohur faza të rëndësishme ndërtimi dhe riorganizimi urban në periudhën romake. Këtë e dëshmon qendra monumentale që ka qenë pikësynimi i gërmimeve dhe zbulimeve të kryera nën drejtimin e francezit Leon Rei, në fillim të shekullit të XX. Pas Luftës së II Botërore, ekipet shqiptare kanë vazhduar nxjerrjen në dritë të saj, si dhe kanë realizuar restaurimet dhe pamjet që shohim sot. Qendra monumentale është organizuar rreth dy godinave kryesore, odeoni dhe monumenti i Agonotetëve. Këto vende mbledhjesh dëshmojnë për karakterin publik të kësaj zone të qytetit, ashtu si dhe një hark triumfi pak më i vonshëm. Dyqanet dëshmojnë për një funksion tregtar aneks. Aspekti religjioz ilustrohet me praninë e një tempulli jonik, të rrethuar me një portik, dhe që lidhet me një godinë të ashtuquajtur prytaneum, si dhe me një faltore e vogël. Së fundmi, një ndërtesë në formë katrore mund të jetë ndoshta një bibliotekë apo augusteum. Në përfundim të studimit të rrënojave të dukshme dhe të dokumentacionit përkatës, parashtrohet trajtimi i funksioneve të monumenteve të ndryshme dhe i elementeve krahasuese të rimëkëmbjes hipotetike të tyre, që më tej transformohen në paraqitjet e informatizuara. Më pas, të gjithë elementët janë bashkuar në një pamje gjithëpërfshirëse të qendrës monumentale romake, ashtu siç paraqitej ajo në fillimin e shek. III të e. sonë. Në pritje të përfundimit të kërkimeve në agora, e cila gjendet vetëm disa qindra metra larg, ky ansambël duket të ketë qenë një kompleks arkitekturor që i kushtohej kultit perandorak, rëndësia e të cilit do të tërhiqte përgjatë shek. II të e. sonë buleterionin, që ende në mënyrë të kujdesshme emërtohet si “monumenti i Agonotetëve”
29
DeLuna, Ruben. "Integrating 3D and 2D computer generated imagery for the comics medium." Texas A&M University, 2004. http://hdl.handle.net/1969.1/1568.
Full textAbstract:
Advances in 3D computer technology have led to aesthetic experimentation
within the comics medium. Comic creators have produced comic books done entirely
with 3D models that are then assembled digitally for the printed page. However, in using
these 3D objects in a comic format, the creators have developed art styles that do not
adhere to the paradigms established by this traditionally 2D medium. More successful
results can be achieved by integrating 3D computer generated imagery with traditional
2D imagery, rather than replacing it.
This thesis develops a method of combining rendered 3D models with 2D vector
graphics to create a comic book art style that is consistent with the traditional medium,
while still taking advantage of the new technology.
30
Li, Guo. "Neural network for optimization of binary computer-generated hologram with printing model /." Online version of thesis, 1995. http://hdl.handle.net/1850/12234.
Full text
31
Leinonen, Emmi. "Copyright implications of computer-generated imagery using the likeness of real people." Thesis, Uppsala universitet, Juridiska institutionen, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-413343.
Full textAbstract:
The Universal Declaration of Human Rights article 27 shows that copyright law has two functions. ‘everyone has the right freely to participate in the cultural life of the community, to enjoy the arts and to share in scientific advancement and its benefits. Everyone has right to protection of the moral and material interests resulting from any scientific, literary or artistic production of which he is the author.’[1] These functions are supporting cultural aspects on society and give a prior right to holder of the copyright to secure and use the work. On the other hand, copyright secures the personality and property rights of the copyright holder. When talking about copyright as an international concept we can state that copyright is not an absolute right, it is limited by the common wellbeing of society, meaning that quoting and getting the information or ideas from other’s work is accepted. Ideas, principles, thoughts, or themes are not included in the scope of copyright protection.[2] Copyright can be created only by a human, but it can be transferred to a legal person like a company. Not that long-ago computer programs were not seen as tangible property and that is why the damages done to the programs were hard to prove as a criminal action.[3] Copyright protects the artistic work during the whole lifetime of author and 70 years after his death. It can be said that copyright and related rights are less protective than industrial registered intellectual property, on contrary, copyright is not limiting the protection to the level of success or requirements, while for example, patent law is very restrictive about the quality of product.[4] Copyright law is a territorial limited law, led by international regulations like the Berne Convention for the Protection of Literary and Artistic Works (hereafter Berne Convention)[5] and European Copyright Directive (hereafter DSM Directive).[6] Photoshop and image manipulation are present in everyday life, this kind of services can be offered even to children for their school portals. Use of computer-generated pictures and films is increasing in campaigns, news and movies. This kind of image technology can be used for making simulations of law cases or “waking up” movie stars from death. The scale of use is endless. The artificial intelligence (hereafter AI) technology behind computer-generated imageries is called deep learning. Deep learning is an advanced type of machine learning and it is used at, for example, computer programs, self-driving cars, and targeted online advertising.[7] The artificial intelligence software makes generating easy and possible for larger user groups and develops images, which brings more legal problems as well. Computer-generated imageries (hereafter CGI) are used for the entertainment industry for different targets and upgrade the film for a new level. In the same time, it can be used for an act of revenge, when the content is defamation the person at the picture, or it can be used for fake news. These kinds of computer-generated imageries are called deep fakes. Sometimes the imageries done by AI or other software are so real that it is almost impossible to recognize the difference with the bare eye, the content of the deep fake can lead the viewer to wrong. The problem of deep fakes has been identified by the governments as well as by the large corporations, for example, Facebook. Facebook, which is one the world’s biggest social media network, has decided to delete and ban deep fakes on its pages according to Monica Bickert vice-president of Facebook. The ban does not apply the parody or satire content, which is one argument that copyright holders are relying on deep fakes.[8] The aim of the thesis is to recognise all aspects of copyright law implications; including the rights of the owner of original work, rights of the owner of new work, rights of the persons that are at the copyright-protected work and rights of the trademark owner if the trademark is used on imagery. [1] The Universal Declaration of Human Rights by the United Nations General Assembly on 10 December 1948 [2] Article 2 of Berne Convention for the Protection of Literary and Artistic Works. September 9, 1886 regulates the scope of the works which are enjoying copyright protection. Guidelines to Berne Convention paragraph 2.2 and 2.3 state that the content itself is not important for copyright protection but the form of the work. Therefore, for example, idea is excluded from the scope of copyright protection. WIPO. Guide to the Berne Convention for the Protection of Literary and Artistic Works. 1978. Retrieved April 25, 2020, from https://www.wipo.int/edocs/pubdocs/en/copyright/615/wipo_pub_615.pdf [3] Cox v Riley (1986) 83 Cr App R 54. The employee erased several programs from the magnetic cards and was charged with criminal damage. Employee argued that he was not guilty because the computer programs were not tangible property. Court held that even though the computer programs were not tangible property the damages done to the cards were enough to be charged in a criminal sentence. [4] Pila, J. Torremans, P. European Intellectual Property Law. 2nd edition. 2019. Oxford. [5] Berne Convention for the Protection of Literary and Artistic Works. September 9, 1886. The latest text of Berne Convention (from 1971 Paris Act plus Appendix) will be used at thesis. [6] Directive (EU) 2019/790 of the European Parliament and of the Council of 17 April 2019 on copyright and related rights in the Digital Single Market and amending Directive 96/9/EC and 2001/29/EC [7] Rouse, M. Definition ‘deep learning’. TechTarget. 2019. Retrieved May 25, 2020, from https://searchenterpriseai.techtarget.com/definition/deep-learning-deep-neural-network [8] Bickert, M. Enforcing Against Manipulated Media. 2020. Retrieved May 9, 2020, from https://about.fb.com/news/2020/01/enforcing-against-manipulated-media/
32
Franceschetto, Giovanni <1996>. "COMPUTER GENERATED IMAGERY INFLUENCERS AS A MARKETING TOOL: A STUDY OF LIL MIQUELA." Master's Degree Thesis, Università Ca' Foscari Venezia, 2020. http://hdl.handle.net/10579/18063.
Full textAbstract:
This work analyses the communication tools that firms can implement to deliver their products and services. In particular, it deals with the Marketing Influence Practice.
It attempts to address specifically the use of social networks by companies to promote their items by relying on innovative figures that characterize a more and more popular trend: the Computer Generated Imagine (CGI) influencers.
After providing a general overview of the evolution of the marketplace and how these personalities, even being not real, influence consumers’ choices, the work studies one of the currently most popular among the digital influencers with the name of Lil Miquela.
The content of the posts published on the Instagram account of the virtual influencer is analyzed as well as the messages that Brud, the LA based startup that manages the profile, spreads with the aim to identify those key inputs that allowed Miquela Sousa to become successful and requested by different fashion and beauty brands.
Factors such as social activism, the allure of uncertainty around her true being (virtual or human), the captivating captions under the posts and the interest generated by the media are explored and discussed. This has been pursued through interviews with experts in this sector and active followers of Miquela and a survey using ANOVA analysis and the Tukey-Kramer Test. The work describes what this virtual personality stands for and the reasons for the media impact value, as highlighted during the Prada Fashion Week in Milan during the SS collection 2018/2019.
The concluding remarks and reflections on implications point to how the use of virtual personalities might be conceptualized also to contribute to social utility.
33
Muller, Thomas. "Synthèse d’image iso-photographique pour la conception de l’apparence assistée par ordinateur." Electronic Thesis or Diss., Paris, CNAM, 2021. http://www.theses.fr/2021CNAM1289.
Full textAbstract:
La notion de « Conception de l’Apparence Assistée par Ordinateur » (CA²O), apparue `a la fin des années 90, est une branche de la CAO traitant plus spécifiquement de l’aspect des matériaux. La CA²O pourrait être un outil déterminant pour la prise de décision lors des phases de conception des produits manufacturés. Pourtant, alors que de nos jours la maquette numérique a presque totalement supplanté la maquette physique en ce qui concerne le choix de la forme, la détermination des couleurs et des matières passe encore essentiellement par la réalisation d’un ou plusieurs prototypes réels. Ce travail de recherche pose la problématique de la prise décision liée `a l’apparence sur la base d’une simulation en images de synthèse. Cette approche pragmatique permettant le lien entre réel et virtuel constitue dans ce domaine un nouveau paradigme qu’on appellera le rendu iso-photographiqueThe so-called “Computer Aided Appearance Design” (CA²D), which emerged in the late 1990s, is a branch of CAD dealing specifically with the appearance of materials.CA²D could be a key tool for decision-making in the design phases of manufactured products. However, while nowadays the digital model has almost completely superseded the physical model as far as the choice of shape is concerned, the determination of colours and materials still essentially requires the production of one or more real prototypes. This research workraises the issues of decision-making related to appearance on the basis of a computer-generated image simulation. This pragmatic approach allowing a link between real and virtual provides in this field a new concept that we shall call iso-photographic rendering
34
Hoffmann, Tammy Coral. "Development and evaluation of a computer-generated individualised written education package for patients following stroke and their carers /." [St. Lucia, Qld.], 2005. http://www.library.uq.edu.au/pdfserve.php?image=thesisabs/absthe18924.pdf.
Full text
35
Tan, Adrian Hadipriono. "A Computer-Generated Model of the Construction of the Roman Colosseum." The Ohio State University, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=osu1354683991.
Full text
36
Cutler, Barbara M. (Barbara Mary) 1975. "Aggregating building fragments generated from geo-referenced imagery into urban models." Thesis, Massachusetts Institute of Technology, 1999. http://hdl.handle.net/1721.1/80525.
Full textAbstract:
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1999.Includes bibliographical references (p. 113-115).
Barbara M. Cutler.
M.Eng.
37
Hazey, Michael A. "Sensitivity comparison evaluation of computer-generated three dimensional surface topography to conventional maxillofacial radiographic imagery." Morgantown, W. Va. : [West Virginia University Libraries], 2006. https://eidr.wvu.edu/etd/documentdata.eTD?documentid=4481.
Full textAbstract:
Thesis (M.S.)--West Virginia University, 2006.Title from document title page. Document formatted into pages; contains x, 220 p. : ill. (some col.). Vita. Includes abstract. Includes bibliographical references (p. 69-74).
38
Quan, Wei. "3-D facial expression representation using statistical shape models." Thesis, University of Central Lancashire, 2009. http://clok.uclan.ac.uk/21147/.
Full textAbstract:
Facial expressions are visible signs of person's affective state, cognitive activity and personality. Automatic recognition of facial expressions is an important component for a wide spectrum of applications including human-computer interfaces, video conferencing, augmented reality and human activity monitoring to mention a few. Facial expression representation is an essential part in the automatic recognition of facial expressions. It is concerned with finding distinguishable features that can be utilised for representing different facial expressions without constraints of age, ethnicity or gender. This thesis reports on research and development in the facial expression representation. The author has proposed two novel methods for representing facial expressions. One is based on the shape space vector (SSV) of the statistical shape model (SSM); the other is based on the SSV of the B-spline statistical shape model (BSSM). The first proposed method uses the SSV of the SSM as a significant feature for representing facial expressions embedded in 3-D facial surfaces. In order to obtain the SSV, a novel model-based surface registration method is proposed that iteratively deforms and matches the model to an unseen new facial surface. Two major stages are included in this method, namely, model building and model fitting. In the model building stage, a SSM is built by using a training data set with estimated correspondences. In the model fitting stage, the built model is adapted to represent the shape of the new facial surface, which has not been included in the training data set. To build the model, the thin plate spline warping has been used so that all of the facial surfaces in the training data set are aligned into a common reference facial surface and the dense correspondences of points between these facial surfaces can be calculated. To fit the model to the new facial surface a modified iterative closest point (ICP) algorithm and least-squares projection on to the estimated shape space, constructed using the training data set, are applied. The second proposed method uses the SSV of the BSSM for facial expression representation. The mddel is built using B-spline control points instead of the surface points as in the SSM based method. In order to obtain the control points of B-spline, a novel method for the B-spline surface fitting has been proposed. The robustness and efficiency of both model-based facial expression representation methods are improved by introducing a multi-resolution scheme in the model fitting stage. The experimental results on simulated and real 3-D facial surfaces show that the proposed methods can effectively provide distinguishable features for facial expression analysis and recognition.
39
Mahal, Bhopinder Singh. "The application of three-dimensional mass-spring structures in the real-time simulation of sheet materials for computer generated imagery." Thesis, Heriot-Watt University, 2010. http://hdl.handle.net/10399/2359.
Full textAbstract:
Despite the resources devoted to computer graphics technology over the last 40 years, there is still a need to increase the realism with which flexible materials are simulated. However, to date reported methods are restricted in their application by their use of two-dimensional structures and implicit integration methods that lend themselves to modelling cloth-like sheets but not stiffer, thicker materials in which bending moments play a significant role. This thesis presents a real-time, computationally efficient environment for simulations of sheet materials. The approach described differs from other techniques principally through its novel use of multilayer sheet structures. In addition to more accurately modelling bending moment effects, it also allows the effects of increased temperature within the environment to be simulated. Limitations of this approach include the increased difficulties of calibrating a realistic and stable simulation compared to implicit based methods. A series of experiments are conducted to establish the effectiveness of the technique, evaluating the suitability of different integration methods, sheet structures, and simulation parameters, before conducting a Human Computer Interaction (HCI) based evaluation to establish the effectiveness with which the technique can produce credible simulations. These results are also compared against a system that utilises an established method for sheet simulation and a hybrid solution that combines the use of 3D (i.e. multilayer) lattice structures with the recognised sheet simulation approach. The results suggest that the use of a three-dimensional structure does provide a level of enhanced realism when simulating stiff laminar materials although the best overall results were achieved through the use of the hybrid model.
40
Liu, Xindi. "The Ashes and the Portal: An immersive stereoscopic experience on Cyclorama." Thesis, Virginia Tech, 2019. http://hdl.handle.net/10919/92801.
Full textAbstract:
the Ashes and the Portal is an immersive stereoscopic animated short capturing the burned library after a fire disaster at Mzuzu University, Malawi, Africa, and it also witnesses the new design of the library from Virginia Tech architecture students. This animated short recreates the burned library and presents the new library design with photo-real image sequences which can immersively bring the audiences onto the site. The Ashes and the Portal utilizes the Cyclorama system, which is a 32 feet diameter and 16 feet tall cylindrical screen with four projectors that can display visual content. The surrounding panels with rendered footage could provide an immersive experience within this semi-public space. This is a collaboration project between the School of Visual Arts and the School of Architecture + Design, also with technical support from the Institute for Creativity, Arts, and Technology. This project explores the potential use of Cyclorama system as a platform for CG works, especially for stereoscopic animation.Master of Fine Arts
The Ashes and The Portal is a computer generated animation tells a story about burned library at Mzuzu University, Malawi, Africa and a new library design from Virginia Tech architecture students. Audience is required to wear a pair of 3D goggles to view the animation inside a giant curved screen which is surrounding the viewer. The photo-real footage of burned library and new library design can visually bring audiences onto the site and provide an immersive experience. This project is a collaboration project between the School of Visual Arts and the School of Architecture + Design, also with technical support from the Institute for Creativity, Arts, and Technology. This is an educational project that explores the potential use of the Cyclorama system as a platform for computer generated media works, especially for stereoscopic animation.
41
Su, Dan. "Target-Dominant Chinese-English Machine Translation." Diss., CLICK HERE for online access, 2004. http://contentdm.lib.byu.edu/ETD/image/etd609.pdf.
Full text
42
Linné, Andreas. "Evaluating the Impact of V-Ray Rendering Engine Settings on Perceived Visual Quality and Render Time : A Perceptual Study." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-19161.
Full textAbstract:
Background. In computer graphics, it can be a time-consuming process to render photorealistic images. This rendering process, called “physically based rendering” uses complex algorithms to calculate the behavior of light. Fortunately, most renderers offer the possibility to alter the render-settings, allowing for a decrease in render time, but this usually comes at the cost of a lower quality image. Objectives. This study aims to identify what setting has the highest impact on the rendering process in the V-Ray renderer. It also examines if a perceived difference can be seen when reducing this setting. Methods. To achieve this, an experiment was done where 22 participants would indicate their preference for rendered images. The images were rendered in V-Ray with different settings, which affected their respective render time differently. Additionally, an objective image metric was used to analyze the images and try to form a correlation with the subjective results. Results. The results show that the anti-aliasing setting had the highest impact on render time as well as user preference. It was found that participants preferred images with at least 25% to 50% anti-aliasing depending on the scene. The objective results also coincided well enough with the subjective results that it could be used as a faster analytical tool to measure the quality of a computer-generated image. Prior knowledge of rendering was also taken into account but did not give conclusive results about user preferences. Conclusions. From the results it can be concluded that anti-aliasing is the most important setting for achieving good subjective image quality in V-Ray. Additionally, the use of an objective image assessment tool can drastically speed up the process for targeting a specific visual quality goal.
43
Lohmeyer, Edwin Lloyd McGuy. "FROM CELLULOID REALITIES TO BINARY DREAMSCAPES: CINEMA AND PERCEPTUAL EXPERIENCE IN THE AGE OF DIGITAL IMMERSION." UKnowledge, 2012. http://uknowledge.uky.edu/art_etds/2.
Full textAbstract:
Technologies in digital cinema are quickly changing the way contemporary filmmakers create films and how audiences currently perceive them. As we move onward into the digital turn, it becomes ever more apparent that the medium of film has been emancipated from its dependence on the photograph. Directors are no longer required to capture the objectively real as it sits before the photographic lens, but can essentially construct it via groundbreaking advancements in computer-generated imagery, motion capture technology, and digital 3D camera systems and display technologies. Since the origins of film, spectators and filmmakers have assumed an existing relationship between reality and the photographic image. Yet digital film technologies now provide us with hyper-facsimiles of reality that are perceived as photographic, but are often created by way of computer processes. Digital cinema currently allows the viewer to inhabit and interact with cinematic realities in unprecedented ways, and it is this contemporary paradigmatic shift from the analog to the digital that has catalyzed fundamentally new ways of looking at the filmic image. In this paper, I will examine the perceptual complexities of contemporary digital film through the lens of these cinematic technologies by examining their impact on the viewer’s experience.
44
Siqueira, Paula Monteiro. "Cinema digital e educação: novas formas de percepção estética no século XXI." Universidade Federal de São Carlos, 2015. https://repositorio.ufscar.br/handle/ufscar/2752.
Full textAbstract:
Made available in DSpace on 2016-06-02T19:39:53Z (GMT). No. of bitstreams: 1
6587.pdf: 1812199 bytes, checksum: 1dabca73767edd87c867bdd4e17ab882 (MD5)
Previous issue date: 2015-02-27The art goes through transformations on elapse of time, as do the resources and techniques used to produce it, and it s transformed as well as the predominant medium of communication alleged experience mediation. At the beginning of the 20th century Benjamin identified this process and analysed its effects, particularly through movies (BENJAMIN, 1987) and nowadays, with digital movie development, we observe several transformations which impact movie s language and the ways that spectators interact with it. Under the hypothesis that techniques applied to digital movies modify the way that spectators interact with the film, we develop our research on defining a cutout on stereoscopy, which produces the depth effect on 3D movies, and the use of CGI (computer generated imagery), which consists in computer created and animated images, having the target to discuss the impact of these resources on spectator s experience of interaction with movies, and more specifically to investigate new features of digital cinema aiming to understand what are the possible changes on movie s language and broached contents, as well as recognizing features of the ways of perception that might come up on this circumstances. For these purposes we develop a theoretical and empirical research grounded on the theoretical references of Critical Theory of Society.
A arte modifica-se no decorrer da história, bem como os recursos e técnicas pelos quais é produzida, e modifica-se também o meio de comunicação predominante como suposta mediação da experiência. No início do século XX, Benjamin identificou esse processo e analisou seus efeitos, sobretudo por meio do cinema (BENJAMIN, 1987a) e atualmente, com o desenvolvimento do cinema digital, observamos diversas transformações que impactam a linguagem cinematográfica e as formas como os espectadores interagem com as mesmas. Sob a hipótese de que técnicas aplicadas ao cinema digital modificam a forma como o espectador interage com o filme, desenvolvemos a nossa pesquisa delimitando um recorte sobre a estereoscopia, que produz o efeito de profundidade no cinema 3D e o uso das CGI (Computer generated imagery), que consiste em imagens criadas e animadas digitalmente, com objetivo de discutir o impacto de tais recursos sobre a experiência do espectador em interação com as obras cinematográficas, e mais especificamente investigar novas características do cinema digital a fim de compreender quais são as possíveis mudanças na linguagem do cinema e conteúdos abordados, bem como reconhecer características das formas de percepção que possivelmente surjam no cenário específico da cultura audiovisual digital do século XXI. Para tanto, desenvolvemos uma pesquisa teórica e empírica fundamentada no referencial teórico da Teoria Crítica da Sociedade.
45
Swan, Richard Heywood. "Deriving Operational Principles for the Design of Engaging Learning Experiences." Diss., CLICK HERE for online access, 2008. http://contentdm.lib.byu.edu/ETD/image/etd2573.pdf.
Full text
46
Berglöf, Olle, and Adam Jacobs. "Effects of Transfer Learning on Data Augmentation with Generative Adversarial Networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259485.
Full textAbstract:
Data augmentation is a technique that acquires more training data by augmenting available samples, where the training data is used to fit model parameters. Data augmentation is utilized due to a shortage of training data in certain domains and to reduce overfitting. Augmenting a training dataset for image classification with a Generative Adversarial Network (GAN) has been shown to increase classification accuracy. This report investigates if transfer learning within a GAN can further increase classification accuracy when utilizing the augmented training dataset. The method section describes a specific GAN architecture for the experiments that includes a label condition. When using transfer learning within the specific GAN architecture, a statistical analysis shows a statistically significant increase in classification accuracy for a classification problem with the EMNIST dataset, which consists of images of handwritten alphanumeric characters. In the discussion section, the authors analyze the results and motivates other use cases for the proposed GAN architecture.Datautökning är en metod som skapar mer träningsdata genom att utöka befintlig träningsdata, där träningsdatan används för att anpassa modellers parametrar. Datautökning används på grund av en brist på träningsdata inom vissa områden samt för att minska overfitting. Att utöka ett träningsdataset för att genomföra bildklassificering med ett generativt adversarialt nätverk (GAN) har visats kunna öka precisionen av klassificering av bilder. Denna rapport undersöker om transferlärande inom en GAN kan vidare öka klassificeringsprecisionen när ett utökat träningsdataset används. Metoden beskriver en specific GANarkitektur som innehåller ett etikettvillkor. När transferlärande används inom den utvalda GAN-arkitekturen visar en statistisk analys en statistiskt säkerställd ökning av klassificeringsprecisionen för ett klassificeringsproblem med EMNIST datasetet, som innehåller bilder på handskrivna bokstäver och siffror. I diskussionen diskuteras orsakerna bakom resultaten och fler användningsområden nämns.
47
Critchfield, Brian L. "Statistical Methods For Kinetic Modeling Of Fischer Tropsch Synthesis On A Supported Iron Catalyst." Diss., CLICK HERE for online access, 2006. http://contentdm.lib.byu.edu/ETD/image/etd1670.pdf.
Full text
48
Barber, Cody. "The Virtual Steamroller: How CGI Paved the Way for 3D's Comeback." Ohio University / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1323194803.
Full text
49
Matulík, Martin. "Modelování a animace biologických struktur." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2018. http://www.nusl.cz/ntk/nusl-377662.
Full textAbstract:
Following work deals with subject matter of digital modelling and animation of biological structures. Software tools for computer generated images (CGI), well proven in common practice, are evaluated, as well as tools for specific activities, available inside chosen software environment. Among vast pool of modelling approaches are discussed tools suitable for creation and representation of selected structures, along with tools essential for their consequent animation. Possible rendering approaches and their parameters in relation to qualities of resulting computer-generated images are discussed as well. Above-mentioned approaches will be consequently utilized for modelling, physical simulation and animation of erythrocyte’s flow throughout blood vessel in following project. Resulting output of that work will be based on series of digital images, suitable for creating video-sequence containing abovementioned animation in end-user digestible form.
50
Louis, Clare. "A study of how the technological advancements in capturing believable facial emotion in Computer Generated (CG) characters in film has facilitated crossing the uncanny valley." Thesis, 2014. http://hdl.handle.net/10539/15791.
Full textAbstract:
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 AfricaIn 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.