Дисертації з теми "Esthétique d'image"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-23 дисертацій для дослідження на тему "Esthétique d'image".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Guilminot, Virginie. "La synthèse d'image animée : au-delà d'une simulation réaliste." Paris 8, 1996. http://www.theses.fr/1996PA081159.
Повний текст джерелаA majority of 3d films and computer graphics respect a realistic aesthetic. On one hand, I will analyse why such totally made images initiate a film or reality and on the other hand, I will try to offer alternativity in order to create an other aesthetic, not being realistic. Softwares need numerous scientific formulas, therefore the author, while manipuling it, will be the main actor to change the situation. This is the main point. Realism exists in every 3d application, such as research, tv, cinema, fiction, school and even often in creation. A few artists managed to escape from realism, i. E. : Joan Stavely, Tamas Waliczky or Michel Bret. Each has its own way of working but they all aim at the same: not to reach realistic simulation. I agree on this point and illustrate my thinking, I made three 3d films with more sensitivity than technical challenge. It is possible to avoid the trap of realism. Indeed, by manipulating and divert the software, one can obtain different 3d computer graphics. Step by step, a new approach to handle and to develop tools apears, and thanks to this, authors can create films other than realistic.
Le, Quyet Tien. "Vers une analyse et une compréhension de la qualité d'image." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALT060.
Повний текст джерелаIn this thesis, the main contributions are to study 2 main aspects of image quality including image aesthetic, image naturalness and the relations between the 2 concepts. More specifically, image aesthetic is the measure of how aesthetically a photo fulfills the observer’s expectation while the image naturalness definition is both related to artifacts induced by some image processing algorithms and to the individual feeling about how a picture matches with image memory. On the side of image aesthetic, the thesis deals with the problem of evaluating the roles of pre-processing operations in image aesthetic assessment. Image aesthetic assessment models based on prior image segmentation (region of interest extraction) and prior image classification (large field / close-up image classification) have been developed and compared with image aesthetic assessment models without pre-processing stages. At the same time different models base either on handcrafted features or learned features have been studied for the purpose of image aesthetic estimation. Based on the obtained results, an image aesthetic assessment model based on image classification and region segmentation has been introduced and evaluated. On the side of image naturalness, image naturalness of standard dynamic range images, especially tone-mapped images have been studied with both subjective and objective methodologies. A subjective experiment has been organized to collect human evaluations about image naturalness first. Then, various objective algorithms have been validated on the collected subjective data for the image naturalness assessment task. This work focuses on the problem of developing a model firstly to estimate if an image looks natural or not to humans and the second purpose is to try to understand how the unnaturalness feeling is induced by a photo: "Are there specific unnaturalness clues or is unnaturalness a general feeling when looking at a photo?". Finally, the relations between the 2 aspects: image aesthetic and image naturalness have been evaluated and discussed
Gaudin, Indicatti Pauline. "L'acte d'image : notes, réflexions, positions : naviguer, ici ou ailleurs, avec (ou sans) son mobile." Thesis, Strasbourg, 2018. http://www.theses.fr/2018STRAC040/document.
Повний текст джерелаAt this time of digital technologies, the profusion of received and shared images, speed and mobility have never been so evident, we can discuss the question of the relationship between gestures, connected objects and creative artistic practices, which can appear as “amateurs”. In a world now localizable, known and recognized by all, the experience of traditional travel would have given way to navigation on the Internet every day? What can cause the presence of this tool in the artist experimentation? How does he use it? Does he show, although, something of this experience? Do new forms appear with the accompaniment of the mobile phone, intelligent? Do they change our perception and relationship to the image? What does the digital environment produce on these forms, which, when they are revealed, or if they are revealed, are contrasting to the so-called "traditional" works of art. They constitute modes of resistance to the "recognized" conceptions of art like those of the work presentation. One of the essential object of the thesis is the reflection on the act of image realized with the mobile, or the gesture “made” often more than the eye "sees" or controls the frame. It is an artistic and reflective experience at the heart of cumulative mobility; where a new work paradigm, modes of diffusion is specifically thought in relation to the captured image
Zhang, Jing. "Prise en compte de l’esthétique dans la gestion des gammes de luminance des images." Electronic Thesis or Diss., Littoral, 2024. http://www.theses.fr/2024DUNK0704.
Повний текст джерелаAesthetic analysis of digital images enhances the visual content's aesthetic quality. By analyzing aesthetic features that influence visual perception through image data, computers can perform tasks like assisted image editing, aesthetic quality enhancement, and filtering for the best image. This thesis merges aesthetic image analysis with high dynamic range (HDR) imaging. We consider both the properties of HDR and the aesthetic characteristics of images during HDR image processing. The aim is to maximize the preservation of the original aesthetic features of images when adjusting HDR image display results, thereby achieving a pleasant visual experience. In this thesis, we propose a composition leading lines reconstruction method and two HDR image auto-adjustment methods. Regarding automatic adjustment of HDR images, we are developing a model based on a neural network to predict the adjustment curve of HDR images, and a model using a convolutional neural network to estimate the exposure adjustment value, by analyzing potential features of HDR images. Both methods automatically enhance the aesthetic quality perception of HDR images on HDR display devices by training neural networls to learn expert editing parameters from an HDR database. In order to analyze the aesthetics of image composition, we propose to reconstruct the leading lines of the image. Just like color, lighting, or the grain of the image, the leading lines among the aesthetic features that need to be analyzed. The proposed method identified implicit leading lines in the image through a line regrouping algorithm. We initially carried out an inter-expert consistency analysis to demonstrate the feasibility of our method. In addition, we propose a metric for comparing the two sets of leading lines
Le, Pen Jessie. "La description d'images dans l'analyse de film." Paris 3, 2007. http://www.theses.fr/2007PA030048.
Повний текст джерелаThe description of images is being explored as a guarantee of objectivity for an interpretation to come. First, the objectivity is questioned through a descriptive practice which tries to define stable relations between the components of the image and language. The image as a sign might find linguistic equivalents to its components. Thus, we study the correspondence between the objects in the image and the signifieds, and between the abstractions and the signifiers, first individually, then as part of narrative modalities and systemic modalities. The analysis of this method shows its ineffectiveness. It fails because it seeks after meaning when it should seek after « signifiance ». Secondly, and as a consequence, we suggest a dynamic description based upon the search of a pertinence and of frames of description. Singularity, as a break in a norm immanent to the film, is the pertinence from which to build a model of description. Following Goffman’s theory, Frame analysis, we define frames of comprehension in the film corresponding to the apprehension of different coherences. This frames once settled, it’s about showing if they evolve homogeneously or if they break the homogeneity, which is called a modalization, producing the springing up of a singularity. This singularity is defined as an event bearing the « signifiance » which the interpretation will use in the end. To describe is thus to confront the frames with their modalizations to make the events spring up. Finally, the application of the method of description put to a test with such a special film as Anticipation of the night by Brakhage enables us to underline its successes and limitations. The frames description allows to reveal cinematographic events full of « signifiance ». Nevertheless we must go deeper into it pragmatically in order to seize the poeticity of certain special films
Lafon, Jacques. "Image et construction : ébauche d'une esthétique de l'image de synthèse." Paris 8, 1997. http://www.theses.fr/1997PA081278.
Повний текст джерелаWhat is a data-driven image? we asked it while the common use of data-driven images through the whole space of media make people blind to their matter. So, commercial works published from 1983 to 1996 were challenged to art works, and specially painting works. We sketch two hypothesis using aristote's rhetoric as investigation method. The first model is the angel: computer images are interfaces between sensible world and intelligible world. The second one is the cast: images are sensitized meshes that take over objects to reveal them, lead and change me into a sensible subject. However, studies show that 3d-simulating images can be described by a plane model as alberti did it in de pictura. Then, the right goal is not to find a travel from me to numeric models, but to ask what does images emerging into conscience? thus, the flesh of images are to be observed for distinguish elements and figures as the angelic performers, the lowest soliciting movements of a ride, a simulated dolphin which does like this person as alberti described. 2d-pixels and 3d-particles are such angels who both help to understand images and constitute its flesh. This show facing ours eyes blurs the pure reason into the tissue of the sensible. From ours eyes to the bodies or to the non-bodies (particles), the same blurring space is stretched
Myszkowski, Nils. "Sensibilité esthétique : Nature, mesure, variabilité." Thesis, Paris 5, 2013. http://www.theses.fr/2013PA05H106.
Повний текст джерелаVisual aesthetic sensitivity refers to the ability to judge the aesthetic properties of works of art,which we commonly describe as “good taste” (Eysenck, 1983). Early framework suggests thatvisual aesthetic sensitivity is a mostly intelligence-independent and personality-independentability (Frois & Eysenck, 1995). This finding led researchers to hypothesize that visual aestheticsensitivity is an “isolated” ability and an innate gift. However, recent research suggests thataesthetic experience and its outcomes can be predicted by personality traits (Furnham &Chamorro-Premuzic, 2004; Furnham & Walker, 2001; McCrae, 2007; Rawlings, Barrantes iVidal, & Furnham, 2000) and is related to mental abilities (Reber, Schwarz, & Winkielman,2004; Silvia, 2006; Smith & Smith, 2006). Following these new findings, the nature of visualaesthetic sensitivity is investigated. First, the metrological qualities of the Visual AestheticSensitivity Test (Götz, 1985) are examined (study 1). Second, it is hypothesized that visualaesthetic sensitivity is related to general intelligence (study 2), some art-specific personalitytraits (study 3) and figural creativity (study 4). Finally, a general model, which proposesaesthetic sensitivity as predicted by intelligence and personality, and predicting creativity, istested (study 5). As hypothesized, aesthetic sensitivity was notably found to be correlated withintelligence, openness to aesthetics, and and figural creativity. The results are discussed as anempirical support of a double-sided (cognitive and conative) conception of visual aestheticsensitivity, and as a support of aesthetic judjement as part of the creative process. Applicationsare discussed, proposing uses of aesthetic sensitivity measures in various domains (design,creative potential identification, marketing, etc.)
Subileau, Thomas. "Contrôle artistique du rendu en synthèse d'images." Thesis, Toulouse 3, 2016. http://www.theses.fr/2016TOU30068/document.
Повний текст джерелаNowadays, computer-generated imagery (CGI) is a standard in digital content creation, as in the context of film production. Visual artists design a model of the virtual scene. The renderer, a specific software, then produces the resulting image, called rendering. Both the 3D model and the renderer rely on physical laws in order to give photorealism. However, for artistic purposes, the visual artist does not necessarily seeks photorealism but is more inclined to care about artistic goals, mostly based on the related work of art. These artistic goals may be in opposition to physically-based rendering, in a similar way to techniques such as chiaroscuro in painting which do not yield a photorealistic result but rather aim at a precise artistic goal. In this PhD thesis, we first define the question of artistic control in rendering and specify three criteria to evaluate editing techniques. We propose a taxonomy to characterise the suitable paradigms to edit rendering. In our work, we focus on behavioural approaches, which properly suit all the evaluation criteria we defined. These methods act on the behaviour of light transport. Following this approach, we propose a theoretical formalism to edit rendering through the teleportation of light transport. We integrate this formalism in the underlying concept of rendering techniques, the rendering equation. We propose a practical tool we call \emph{RayPortals}. Using RayPortals, the rendering is edited using a pair of surfaces, input and output, defining the teleportation in 3D space of ligth transport. We integrate RayPortals in usual rendering techniques. We compare to previous work and also show some novel results. Ultimately, we propose a preliminary analysis of the path-space structure and summarize the future works
Oh, Jin-Kyeong. "La répétition d'images et d'objets du dadaïsme au pop art (des années dix aux années soixante)." Paris 1, 1993. http://www.theses.fr/1993PA010597.
Повний текст джерелаThe repetition of images and of objects is a remarkable and constant phenomenon in the modern ar. We can define three categories of works of art in which the repeated images and objects appear. First, the iconographical significance of the repetition due to the techniques of reproduction connected with the modern industrial society ; second, the formal abstract effect of the repeated figurative images or objects ; third, psychological effect of the repetition : feelings of strangeness, anguihs and obsession. In modern art, the artists use the monotonous repetition to search for their own artistic language and to prodduce, paradoxically, a variation of style. Even though it is a matter of the stereotyped and depersonalized repetition, as long as there is a will of artists to pursue the aesthetic and plastic investigations and experimentations, the works of art will always have the value of originality and of uniqueness
Vadori, Nadia. "Du mouvant : processus somatique de création individuelle et collective d'images et de formes vivantes." Electronic Thesis or Diss., Paris 8, 2014. http://www.theses.fr/2014PA080004.
Повний текст джерелаThis research is an attempt to establish a process of artistic creation, simultaneously theoretical and practical, contributing to the conception of new image modalities in the art field and offering alternatives to representation. Images –fluid, autopoietic– are considered here more as continuous translations than fixed shapes. They are living entities, constituting themselves at their limits, always on the verge of attaining consistency or dissolving. We start with movement, Bergsonian duration, putting ourselves inside it in order to embrace the continual flux of our bodies and of things. We enter into an open process based upon a groundwork of fluid somatic experimentation involving both (1) explorations without images (explorations antecedent to the images produced by the nervous system) and (2) a multiplicity of poetic images engendered by the process itself. We join to these practices that of a philosophy experienced in action, involving concepts in the creative process, movement, and dance. We come to experience and conceive a threshold of trembling on which ordinary perception flickers. We develop modalities of the gaze that attempt to open bodies/spaces, liberating them from set images or too-fixed identities. At issue is not merely seeing with skin, liquids, bones, but espousing the void at the heart of things and attempting to see with "the eyes of the void" in order that images be transmuted continually into their anagram: magies [spells]. We may then connect to the fluidic aspects of life and a new gentleness may flow between bodies and categories
Masse, Jean-François. "Applications dentaires du logiciel Photoshop." Master's thesis, Université Laval, 2004. http://hdl.handle.net/20.500.11794/18089.
Повний текст джерелаBernier, Stéphanie. "Pourquoi la fiction? : la fiction dans l'écriture concentrationnaire de Jorge Semprun et d'Imre Kertész : une question éthique et esthétique." Mémoire, Université de Sherbrooke, 2013. http://hdl.handle.net/11143/6492.
Повний текст джерелаVadori, Nadia. "Du mouvant : processus somatique de création individuelle et collective d'images et de formes vivantes." Thesis, Paris 8, 2014. http://www.theses.fr/2014PA080004.
Повний текст джерелаThis research is an attempt to establish a process of artistic creation, simultaneously theoretical and practical, contributing to the conception of new image modalities in the art field and offering alternatives to representation. Images –fluid, autopoietic– are considered here more as continuous translations than fixed shapes. They are living entities, constituting themselves at their limits, always on the verge of attaining consistency or dissolving. We start with movement, Bergsonian duration, putting ourselves inside it in order to embrace the continual flux of our bodies and of things. We enter into an open process based upon a groundwork of fluid somatic experimentation involving both (1) explorations without images (explorations antecedent to the images produced by the nervous system) and (2) a multiplicity of poetic images engendered by the process itself. We join to these practices that of a philosophy experienced in action, involving concepts in the creative process, movement, and dance. We come to experience and conceive a threshold of trembling on which ordinary perception flickers. We develop modalities of the gaze that attempt to open bodies/spaces, liberating them from set images or too-fixed identities. At issue is not merely seeing with skin, liquids, bones, but espousing the void at the heart of things and attempting to see with "the eyes of the void" in order that images be transmuted continually into their anagram: magies [spells]. We may then connect to the fluidic aspects of life and a new gentleness may flow between bodies and categories
Sauvaget, Catherine. "De la synthèse d'images expressive aux effets bande déssinée : vers un outil d'aide à la création artistique." Paris 8, 2011. http://www.theses.fr/2011PA083398.
Повний текст джерелаWe present a tool for assisting artistic creation which produce a wide variety of image stylizations with “comics” effects. The system gives to the user an important role in the control of stylization. Starting from an artistic analysis, we propose a system based on the most important criteria in the artistic process of picture creation. We present models coming up to artists expectations. First, we present a model semi-automatically generating a depth map to stylize images while avoiding depth problems. It can also produce atmospheres used by artists to induce specific psychological effects to the observer. Then, we propose two models showing the interest of harmonizing images and using the contrast of quantity defined by Johannes Itten. The first one ensures this harmony in images like photographs or illustrations; based on the same harmony, the second one offers, by extension, a coloring aid for sketches to obtain harmonious images at the early stages of creation. Our last model deals with the effects of light contained in the images. It allows to stylize different kinds of lighting effects by moving, reshaping or giving them a style developed from well-known artistic movements. We conclude with our tool contributions and we present possible improvements as well as our plans for the future
Ciciliato, Vincent. "GLITCH(s) IMAGO-SONORE(s) Du processus d'objectivation par découpe et synchronisation son-image à une esthétique du micro-mouvement." Phd thesis, Université de Picardie Jules Verne, 2010. http://tel.archives-ouvertes.fr/tel-00627733.
Повний текст джерелаSuret-Canale, Michel. "D'un atelier à l'autre : au regard des faits." Paris 1, 1996. http://www.theses.fr/1996PA010641.
Повний текст джерелаThe thesis consists of a critical self-analysis and the clarification of the dialectical relationship (theoretical practical) supporting the artistic work of the author. The aim of this research, formalised by a dialogue between sight and vision, could be resumed as follows : in an image, to show that part which is shadow, the blindness from which one's viewpoint emerges and of which the critical image preserves the memory. The objective, uncertain, is to succed, both through the successive hybridzation of techniques and critical reflection, in the creation of composite images. Composite images, images which attest banally to a ça a été, everyday images that have rid themselves of the strategic stakes of art, free to return to a common ground, not on the grounds of artistic cliche, but rather the common ground of everday life, espace de ressemblement ; because once idle, the image comes to resemble us, to bring us together. Failure is not feared, it appears, to the contrary, to be a necessary condition to the succes of the project
Rebeschini, Nicola. "Image corporelle, Corps d'images. Processus de création et œuvre aujourd'hui. Hypothèses pour une esthétique organique : Étude comparative à partir de l'installation-performative Sketches / Notebook de Meg Stuart (Berlin, 2013)." Thesis, Sorbonne Paris Cité, 2017. http://www.theses.fr/2017USPCA138.
Повний текст джерелаThe body is being-in-the-world. The body is the image's-being-alive, and thus, the body is an inhabited-image. The image-body gives place to the sensitive space within its advent. Can the Being, as Nature, be visible through images or gestures ? Is there a specificity in certain filmic or performative fragments about the figure of the body and forms taken by a persona ? If this specificity is proven, through which means of the aesthetic creation can these images or gestures be created and how do they impact the artwork ? What are the devices of material and immaterial sensitive sharing of space, as settled by the artwork, that allow the onlooker to live the experiment of the emergence of being through the image or the gesture which he is witnessing ? This study is based upon the experience of practical and theoretical research on artworks. The meaning of said research is rooted in the experience of creation concerning performative dance, cinema of the body and, in a wider perspective, dance cinema. The quest for a theory of the sensitive, in our work, has its foundations, first in the study of the process involved in transdisciplinary creation involving body and images / images and body in motion ; second, in the study of moving pictures generating an experience of the body's presence, considered as specific to human matters. In light of this point of view, our project, through the process of performative creation, is to study the conditions which give birth to the upsurge of what we call a body of images and, in filmic artwork, to grasp and describe the modalities through which what we define as a corporeal image appear. Concerning practical research, we have taken part in the creative team of Meg Stuart's performative setup, Sketches / Notebook, and thus assembled a set of documents which we have analysed and compared, all along our theoretical research, to a complementary set made of performative and, most of all, filmic artworks (among which are included Pina Bausch's Die Klage der Kaiserin and Béla Tarr's Sátántángo). This research gave us the opportunity to call to mind the numerous links existing between different philosophical and aesthetical points of view, as well as to deepen our construction of the janus bifrons concept of corporeal image / body of images, as related to the expression of the persona in an environment made of setups and symbols which our research designates as specific to an organic aesthetic. In fact, we recognize in specific fragments of these filmic or scenic artworks the creative power of sensitive space ; the arrangement of setups within the image or within the gesture, able to operate a mutation of the space of signs and their reception. Therefore, it is our understanding that, regarding the creation process, some performative fragments and some images appear to participate in protocols in creative experience which, in a more suitable manner than others, lead, or even give birth to images of the body as images of a persona, through the presence, all together individual and universal, of the human being as the anachronistic sign of a mortal presence
Hsieh, Chenwei. "Processus de création d'un système d'images interactives pour le spectacle vivant : proposition d'une méthode de développement rapide et mise en oeuvre d'une structure d'un système d'interactivité multi-niveaux et multi-sources." Paris 8, 2013. http://octaviana.fr/document/170326594#?c=0&m=0&s=0&cv=0.
Повний текст джерелаIn this thesis, I try to present my process to create an interactive system in a live performance, specifically the dance and musical improvisation made collectively with several artists: performers, composers and creators of the interactive image. The first part is the artistic research about related artists’ works in their live performances. The technical research is the subject of the second part. It consists of my experience about the technology, hardware and software in the development of interactive creations, especially the sensor system of sound and movement. In the end, I propose a structure of system with the multiple-levels and interactive sources. It is a full process to create diversified mapping interactive system. The main goal of the process is to create a faster and more intuitive interactive program. It includes a structure of multiple- level scenes controls, the reusable and independent sensors systems by using the OSC protocol, and the creative function module in platform Unity with multiple input controls
Bist, Cambodge. "Combining aesthetics and perception for display retargeting." Thesis, Rennes 1, 2017. http://www.theses.fr/2017REN1S061/document.
Повний текст джерелаThis thesis presents various contributions in display retargeting under the vast field of High Dynamic Range (HDR) imaging. The motivation towards this work is the conviction that by preserving artistic intent and considering insights from human visual system leads to aesthetic, comfortable and efficient display retargeting
Chamaret, Christel. "Color harmony : experimental and computational modeling." Thesis, Rennes 1, 2016. http://www.theses.fr/2016REN1S015/document.
Повний текст джерелаSince the consumption of digital media exploded in the last decade, making aesthetic pictures quickly - with or without artistic expertise - is more than ever a research topic. Different axis of investigations remain possible: high resolution, high dynamic range or wide color gamut. Additionally to these objective image properties, more perceptual and artistic insights could be of benefit to any user manipulating pictures. In such context, this thesis deals with the topic of Color Harmony. The literature related to this topic is limited, but involves many different scientific areas: color science, image processing and psychology and so on. The validity of collected data is questionable due to their limitation to two- or three-colors patches. The models fitted from these data remain non-exploitable on natural pictures. Other models depicting rules or areas on color wheel lack scientific guidelines for their utilization. Nonetheless, some algorithms employing color harmony theory and models as a core concept showed up in the literature, but suffered from being quantitatively tested and validated. In this thesis, two views are put in perspective in order to respond to the previous statements: an experimental and a computational approaches. The conducted experiment allowed observing some effects with an eye-tracking protocol, never applied before with a task on color harmony assessment. From the collected data of our experimental work, we designed a method to generate a ground truth, which would serve to the validation of the two proposed computational methods. First, we improved an existing architecture for automatic color harmonization and demonstrated exhaustively the benefit of our approach. As a second computational contribution, a novel quality metric is introduced that integrates the concepts of visual masking and color harmony. Thus, we may predict which areas would be perceived harmonious regarding its neighborhood and then the potential masking effects. As a last contribution, two editing tools made accessible the color harmony theory through a hidden formulation of it and a user-friendly and intuitive interface
Kang, Chen. "Image Aesthetic Quality Assessment Based on Deep Neural Networks." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASG004.
Повний текст джерелаWith the development of capture devices and the Internet, people access to an increasing amount of images. Assessing visual aesthetics has important applications in several domains, from image retrieval and recommendation to enhancement. Image aesthetic quality assessment aims at determining how beautiful an image looks to human observers. Many problems in this field are not studied well, including the subjectivity of aesthetic quality assessment, explanation of aesthetics and the human-annotated data collection. Conventional image aesthetic quality prediction aims at predicting the average score or aesthetic class of a picture. However, the aesthetic prediction is intrinsically subjective, and images with similar mean aesthetic scores/class might display very different levels of consensus by human raters. Recent work has dealt with aesthetic subjectivity by predicting the distribution of human scores, but predicting the distribution is not directly interpretable in terms of subjectivity, and might be sub-optimal compared to directly estimating subjectivity descriptors computed from ground-truth scores. Furthermore, labels in existing datasets are often noisy, incomplete or they do not allow more sophisticated tasks such as understanding why an image looks beautiful or not to a human observer. In this thesis, we first propose several measures of subjectivity, ranging from simple statistical measures such as the standard deviation of the scores, to newly proposed descriptors inspired by information theory. We evaluate the prediction performance of these measures when they are computed from predicted score distributions and when they are directly learned from ground-truth data. We find that the latter strategy provides in general better results. We also use the subjectivity to improve predicting aesthetic scores, showing that information theory inspired subjectivity measures perform better than statistical measures. Then, we propose an Explainable Visual Aesthetics (EVA) dataset, which contains 4070 images with at least 30 votes per image. EVA has been crowd-sourced using a more disciplined approach inspired by quality assessment best practices. It also offers additional features, such as the degree of difficulty in assessing the aesthetic score, rating for 4 complementary aesthetic attributes, as well as the relative importance of each attribute to form aesthetic opinions. The publicly available dataset is expected to contribute to future research on understanding and predicting visual quality aesthetics. Additionally, we studied the explainability of image aesthetic quality assessment. A statistical analysis on EVA demonstrates that the collected attributes and relative importance can be linearly combined to explain effectively the overall aesthetic mean opinion scores. We found subjectivity has a limited correlation to average personal difficulty in aesthetic assessment, and the subject's region, photographic level and age affect the user's aesthetic assessment significantly
Kuo, Li-Chen. "Le noir comme invention du cinéma : matière, forme, dispositif." Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCA118/document.
Повний текст джерелаEven though black is the antipode of light it is nevertheless inseparable from the world of cinema. What is black in cinema? A figure of shadow or darkness in the image that is also present as such. Black without representation and with its singular physical reality. This blackness is above all a technical condition which is hidden but which plays a decisive role in the production of optical illusions and the creation of fiction. It is also omnipresent in the entire process of making the cinematographic image. Black plays with light and conditions visibility and invisibility. In this sense it invents cinema. Black also offers another way of understanding what cinema is and how it works. This study will first deal with the material aspect of photography: photochemical blackening and the ideas it suggests as a process of image formation and dissolution. I will then portray the different effects produced by black- the black shape a rhetorical and mechanical tool. When it intervenes as a form in the image, of the image, and between the image. Finally, I will discuss how black can be an invading device of the screen and the projection space and reveal its role as a visual spectacle apparatus: the construction of an access to illusion and revelation. Each part of this outline will be dealt with in a historical, technical and aesthetic way. We will see in particular in artistic and experimental attempts that the emphasis on black makes it possible to reveal the characteristics of the cinematographic medium or even to re-invent cinema. This quest for blackness is revealed as a quest for the nature of cinema. A nature that the film industry is trying to erase. Black makes you see but it makes you see differently
Hawey, Dave. "Création d'images numériques : esthétique du temps japonais et méthodologie de perfectionnement tirée des arts martiaux traditionnels japonais." Thèse, 2012. http://constellation.uqac.ca/2515/1/030298754.pdf.
Повний текст джерела