Дисертації з теми "Synthèse vidéo"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-25 дисертацій для дослідження на тему "Synthèse vidéo".
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.
Rocher, Pierre-Olivier. "Transmodalité de flux d'images de synthèse." Thesis, Saint-Etienne, 2014. http://www.theses.fr/2014STET2026/document.
The use of video as an information dissemination support has become preponderant during the last few years. According to some analysts, by 2017 approximately 90% of the world's bandwidth will be consumed by video streaming services. These services have encouraged cloud gaming solutions to become more democratic. Such solutions have been devised in the context of strong development of the cloud-computing paradigm, and they were driven by the proliferation of mobile devices as well as growing network quality. The technologies used in this kind of solutions refer to as remote rendering. They allow the execution of multiple applications, while maximizing the number of clients per server. Thus, it is essential to control the necessary bandwidth to allow the required functionality of various services. The existing cloud gaming solutions in the literature use various methods of video compression to transmit images between sever and clients (pixels reigns supreme). However, there are various other ways of encoding digital images, including parametric map storage and a number of studies encourage this approach (for both image and video). In this thesis, we propose a hybrid representation of space in order to reduce the bit rate. Our approach utilizes both pixel and parametric approaches for the compression of video stream. The use of two compression techniques requires defining the area to be covered by different encoders. This is accomplished by including user to the life cycle of rendering, and attending to the area mostly concerned to the user. In order to identify the area an eye-tracker device was used on several games and several testers. We also establish a correlation between the characteristics of images and the type of game. This helps to identify areas that the player looks directly or indirectly (“maps of selective attention"), and thus, encoders are manager accordingly. For this thesis, we details and implement the architecture and algorithms for such multi-model encoder (which we call "transmodeur") as proof of concept. We also provide an analytical study of out model and the influence of various parameters on transmodeur and describe in effectiveness through an objective study. Our transmodeur (rendering system) has been successfully integrated into XLcloud project for rendering purposes. A number of improvement (especially in performance) will be required for production use, but it is now possible to use it smoothly using spatial resolutions slightly lower than 720p at 30 frames per second
Moinard, Matthieu. "Codage vidéo hybride basé contenu par analyse/synthèse de données." Phd thesis, Telecom ParisTech, 2011. http://tel.archives-ouvertes.fr/tel-00830924.
Chevrier, Christine. "Génération de séquences composées d'images de synthèse et d'images vidéo." Nancy 1, 1996. http://www.theses.fr/1996NAN10121.
The visual impact assessment of architectural projects in urban environments is usually based on manual drawings, paintings on photographs, scale models or computer-generated images. These techniques are either too expensive or not realistic enough. Strictly using computer images means requiring an accurate 3D model of the environment. Computing such a model takes a long time and the results lack of visual accuracy. Our technique of overlaying computer generated images onto photographs of the environment is considerably more effective and reliable. This method is a promising solution regarding computation time (no accurate 3D model of the environment) as weIl as visual realism (provided by the photograph itself). Such a solution requires nevertheless to solve lots of problems in order to get geometrical and photometrical coherence in the resulting image. To this end, image analysis and image synthesis methods have to be designed and developed. The method is generalized to produce an animated film, and can furthermore greatly increase the realism of the simulation. My Ph. D. Work was to test and integrate various image analysis and synthesis techniques for the composition of computer generated images with pictures or video film. This report explains the steps required for a realistic encrustation. For each of these steps, various techniques were tested in order to be able to choose the most suitable solutions according to the state of the most recent researches and to the applications we were dealing with (architectural and urban projects). The application of this work was the simulation of the Paris Bridges illumination projects. Concurrently to this work, I present a new method for the interpolation of computer images for the generation of a sequence of images. This method requires no approximation of the camera motion. Since video images are interlaced, sequences of computer images need to be interleaved too. The interpolation technique we propose is capable of doing this
Beaumesnil, Brice. "Suivi labial couleur pour analyse-synthèse vidéo et communication temps-réel." Pau, 2006. http://www.theses.fr/2006PAUU3048.
The objective of this thesis is to extract and to track relevant primitives of the mouth in a nonconstrained environment (typically o_ce lighting) to make a realistic animation of a synthetic 3D face model in real-time without audio information. We sought to study various existing methods to adapt them to our problem. First we define a lip hue based on a non-linear color space (little sensitive to lighting variation) in order to exhibit very distinctly skin and lip hue areas on the speaker's face. This hue is then segmented by a clustering algorithm to be able to detect the position of the mouth and its contours. In order to make the algorithm more robust we use synthesis information (feedback loop) of the face to guide the mouth analysis. Low-level methods give us the avantage not to use a database compared to many existing works (typically AAMs). Moreover, their dynamic control ensures a great robustness to the lighting exposition and to the various types of speaker's skin. With this work we have realized a global analysis/synthesis chain (going from the video capture of the speaker until the clone animation). An operational prototype enables us to make animations in real time with many speakers under various types of lighting
Ong, Lolet Yin-Ty. "Techniques numériques appliquées à la synthèse, aux traitements d'image et à la production vidéo." Paris 8, 1998. http://www.theses.fr/1998PA081695.
Rempulski, Nicolas. "Synthèse dynamique de superviseur pour l'exécution adaptative d'applications interactives." Thesis, La Rochelle, 2013. http://www.theses.fr/2013LAROS407/document.
This PhD thesis has for objective to propose solutions to interactive storytelling problems. We aim to propose a design method for the authors, as well as a logic of execution using this model to control the narrative unfolding. We apply our works in the video games context, but wish to address interactive storytelling in a wider dimension. We so approach the interactive story as a breakdown of the classic storytelling. Indeed, interactive storytelling creation process is not any more only under the author responsability, but also involves spectators. Through a review of the classic storytelling, we thus wish, at first, to formalize storytelling and its stakes. We use then the concept of ”œuvre en mouvement” to identify processes and actors involved in this creation process of a work, and thus to define the stakes in our research works. We propose an interactive storytelling mode base on automata. This one allows a controland a check on possible narratives, during design as well as dynamically while producing the story. However this formalism is complex to handle by authors. So, we formulate a top-level model, based on storytelling concepts, allowing authors to create an interactive story model using concepts they know. This model is then converted into our automaton based model. The latter serves then as referent for the dynamic control of the interactive storytelling, done by a supervisor multi-agents. This one, by observing produced events in the video game, is then able of controlling and guarantee the quality criteria specified by authors. We propose an implementation of our approach in a framework, including authoring tools to edite our models. We also implements automata check and supervision algorithms necessary to control video game virtual universe
Racapé, Fabien. "Mise en Œuvre de Techniques d'Analyse/Synthèse de Texture dans un Schéma de Compression Vidéo." Phd thesis, INSA de Rennes, 2011. http://tel.archives-ouvertes.fr/tel-00680826.
Goujet, Raphaël. "Hero.coli : a video game empowering stealth learning of synthetic biology : a continuous analytics-driven game design approach." Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCB175.
Video games have demonstrated their value as a hobby and as a pedagogic tool, both in academic and professional fields. However, learning video games have to integrate pedagogical strategies and be fine-tuned to be efficient and adopted. Synthetic biology is an emerging field focusing on engineering living systems to achieve controlled functions. It shares concepts with crafting and engineering games. We designed the first synthetic biology crafting game, named Hero.Coli, for popularization and learning. In order to engage both forced and voluntary users, ie students and citizens, our main pedagogical strategy is stealth learning. This means creating an educational game with no interruption in the experience - due to explicit learning or assessment phases -, mimicking successful mainstream games. I used embedded analytics to continuously refine this new pedagogical tool, by spotting the bottlenecks and issues in level design, the eventual misconceptions revealed in posttests, and the learning successes. I validated the usefulness of the game by comparing pre- and posttests of players (n=89). I found an average of 32 percentage point increase between pretest and posttest correct answer rate per question. The higher achievements stemmed mainly from higher-order thinking questions as compared to lexical questions. This is in line with our expectation from the chosen stealth learning strategy, which prioritizes function - game mechanics - over lexicon. I then correlated different user tracking parameters to their posttest scores. Lastly, by analyzing surveys, we also revealed that interest in biology is more critical than education to explain the variance in learning. These results could lead to future adaptive learning improvements including user-tailored feedbacks, in-game or in-class. Overall, the Hero.coli framework facilitates future implementations of game-based learning solutions by exemplifying a methodological approach of game development: design, tracking and analytics, quick iteration and testing, and final evaluation
Roquier, Ghislain. "Etude de modèles flux de données pour la synthèse logicielle multiprocesseur." Rennes, INSA, 2004. http://www.theses.fr/2008ISAR0020.
Parallelism is a universal characteristic of modern computing platforms, from multi-core processorsto programmable logic devices. The sequential programming paradigm is no longer adapted in thecontext of parallel and distributed architectures. The work presented in this thesis document findtheir foundation in the AAA methodology to build parallel programs based on an high-level representationsof both application and architecture. This work has enabled to extend the class of applications that can be modelled by the specification of new graph formalism. The final part of the document shows our involvement in the MPEG RVC framework. The RVC standard intends to facilitate for building the reference codecs offuture MPEG standards, which is based on dataflow to build decoder using a new dataflow languagecalled CAL. This work has enabled to specify and develop a software synthesis tool that enables anautomatic translation of dataflow programs written in CAL
Tiger, Guillaume. "Synthèse sonore d'ambiances urbaines pour les applications vidéoludiques." Thesis, Paris, CNAM, 2014. http://www.theses.fr/2015CNAM0968/document.
In video gaming and interactive media, the making of complex sound ambiences relies heavily on the allowed memory and computational resources. So a compromise solution is necessary regarding the choice of audio material and its treatment in order to reach immersive and credible real-time ambiences. Alternatively, the use of procedural audio techniques, i.e. the generation of audio content relatively to the data provided by the virtual scene, has increased in recent years. Procedural methodologies seem appropriate to sonify complex environments such as virtual cities.In this thesis we specifically focus on the creation of interactive urban sound ambiences. Our analysis of these ambiences is based on the Soundscape theory and on a state of art on game oriented urban interactive applications. We infer that the virtual urban soundscape is made of several perceptive auditory grounds including a background. As a first contribution we define the morphological and narrative properties of such a background. We then consider the urban background sound as a texture and propose, as a second contribution, to pinpoint, specify and prototype a granular synthesis tool dedicated to interactive urban sound backgrounds.The synthesizer prototype is created using the visual programming language Pure Data. On the basis of our state of the art, we include an urban ambiences recording methodology to feed the granular synthesis. Finally, two validation steps regarding the prototype are described: the integration to the virtual city simulation Terra Dynamica on the one side and a perceptive listening comparison test on the other
Ali, Karim Mohamed Abedallah. "Architectures parallèles reconfigurables pour le traitement vidéo temps-réel." Thesis, Valenciennes, 2018. http://www.theses.fr/2018VALE0005/document.
Embedded video applications are now involved in sophisticated transportation systems like autonomous vehicles. Many challenges faced the designers to build those applications, among them: complex algorithms should be developed, verified and tested under restricted time-to-market constraints, the necessity for design automation tools to increase the design productivity, high computing rates are required to exploit the inherent parallelism to satisfy the real-time constraints, reducing the consumed power to extend the operating duration before recharging the vehicle, etc. In this thesis work, we used FPGA technologies to tackle some of these challenges to design parallel reconfigurable hardware architectures for embedded video streaming applications. First, we implemented a flexible parallel architecture with two main contributions: (1)We proposed a generic model for pixel distribution/collection to tackle the problem of the huge data transferring through the system. The required model parameters were defined then the architecture generation was automated to minimize the development time. (2) We applied frequency scaling as a technique for reducing power consumption. We derived the required equations for calculating the maximum level of parallelism as well as the ones used for calculating the depth of the inserted FIFOs for clock domain crossing. As the number of logic cells on a single FPGA chip increases, moving to higher abstraction design levels becomes inevitable to shorten the time-to-market constraint and to increase the design productivity. During the design phase, it is common to have a space of design alternatives that are different from each other regarding hardware utilization, power consumption and performance. We developed ViPar tool with two main contributions to tackle this problem: (1) An empirical model was introduced to estimate the power consumption based on the hardware utilization (Slice and BRAM) and the operating frequency. In addition to that, we derived the equations for estimating the hardware resources and the execution time for each point during the design space exploration. (2) By defining the main characteristics of the parallel architecture like parallelism level, the number of input/output ports, the pixel distribution pattern, etc. ViPar tool can automatically generate the parallel architecture for the selected designs for implementation. In the context of an industrial collaboration, we used high-level synthesis tools to implement a parallel hardware architecture for Multi-window Sum of Absolute Difference stereo matching algorithm. In this implementation, we presented a set of guiding steps to modify the high-level description code to fit efficiently for hardware implementation as well as we explored the design space for different alternatives in terms of hardware resources, performance, frequency and power consumption. During the thesis work, our designs were implemented and tested experimentally on Xilinx Zynq ZC706 (XC7Z045- FFG900) evaluation board
Pavie, Hugues. "Synthèse d'images texturées : application au domaine de la production en télévision." Compiègne, 1994. http://www.theses.fr/1994COMPD682.
Wang, Yaohui. "Apprendre à générer des vidéos de personnes." Thesis, Université Côte d'Azur, 2021. http://www.theses.fr/2021COAZ4116.
Generative Adversarial Networks (GANs) have witnessed increasing attention due to their abilities to model complex visual data distributions, which allow them to generate and translate realistic images. While realistic \textit{video generation} is the natural sequel, it is substantially more challenging w.r.t. complexity and computation, associated to the simultaneous modeling of appearance, as well as motion. Specifically, in inferring and modeling the distribution of human videos, generative models face three main challenges: (a) generating uncertain motion and retaining of human appearance, (b) modeling spatio-temporal consistency, as well as (c) understanding of latent representation. In this thesis, we propose three novel approaches towards generating high-visual quality videos and interpreting latent space in video generative models. We firstly introduce a method, which learns to conditionally generate videos based on single input images. Our proposed model allows for controllable video generation by providing various motion categories. Secondly, we present a model, which is able to produce videos from noise vectors by disentangling the latent space into appearance and motion. We demonstrate that both factors can be manipulated in both, conditional and unconditional manners. Thirdly, we introduce an unconditional video generative model that allows for interpretation of the latent space. We place emphasis on the interpretation and manipulation of motion. We show that our proposed method is able to discover semantically meaningful motion representations, which in turn allow for control in generated results. Finally, we describe a novel approach to combine generative modeling with contrastive learning for unsupervised person re-identification. Specifically, we leverage generated data as data augmentation and show that such data can boost re-identification accuracy
Hueber, Thomas. "Reconstitution de la parole par imagerie ultrasonore et vidéo de l'appareil vocal : vers une communication parlée silencieuse." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2009. http://pastel.archives-ouvertes.fr/pastel-00005707.
Ferland, François. "Interfaces graphiques tridimentionnelles de téléopération de plateformes robotiques mobiles." Mémoire, Université de Sherbrooke, 2009. http://savoirs.usherbrooke.ca/handle/11143/1475.
Calemme, Marco. "Codage de carte de profondeur par déformation de courbes élastiques." Thesis, Paris, ENST, 2016. http://www.theses.fr/2016ENST0048/document.
In multiple-view video plus depth, depth maps can be represented by means of grayscale images and the corresponding temporal sequence can be thought as a standard grayscale video sequence. However depth maps have different properties from natural images: they present large areas of smooth surfaces separated by sharp edges. Arguably the most important information lies in object contours, as a consequence an interesting approach consists in performing a lossless coding of the contour map, possibly followed by a lossy coding of per-object depth values. In this context, we propose a new technique for the lossless coding of object contours, based on the elastic deformation of curves. A continuous evolution of elastic deformations between two reference contour curves can be modelled, and an elastically deformed version of the reference contours can be sent to the decoder with an extremely small coding cost and used as side information to improve the lossless coding of the actual contour. After the main discontinuities have been captured by the contour description, the depth field inside each region is rather smooth. We proposed and tested two different techniques for the coding of the depth field inside each region. The first technique performs the shape-adaptive wavelet transform followed by the shape-adaptive version of SPIHT. The second technique performs a prediction of the depth field from its subsampled version and the set of coded contours. It is generally recognized that a high quality view rendering at the receiver side is possible only by preserving the contour information, since distortions on edges during the encoding step would cause a sensible degradation on the synthesized view and on the 3D perception. We investigated this claim by conducting a subjective quality assessment test to compare an object-based technique and a hybrid block-based techniques for the coding of depth maps
Conze, Pierre-Henri. "Estimation de mouvement dense long-terme et évaluation de qualité de la synthèse de vues. Application à la coopération stéréo-mouvement." Phd thesis, INSA de Rennes, 2014. http://tel.archives-ouvertes.fr/tel-00992940.
Jerbi, Khaled. "Synthese matérielle haut niveau des programmes flot de données." Rennes, INSA, 2012. https://tel.archives-ouvertes.fr/tel-00827163.
The evolution of video processing algorithms involved the advent of several standards. These standards present many common algorithms but designers are not able to reuse them because of their monolithic description. To solve this problem, iso/iec mpeg committee created the reconfigurable video coding (rvc) standard based on the idea that processing algorithms can be defined as a library of components that can be updated separately. Thus, these components of the modular library are standardized instead of the whole decoder. Mpeg rvc framework aims at providing a unified high-level specification of current mpeg coding technologies using a dataflow language called cal actor language (cal). Rvc presents also a compilation framework of the cal for hardware and software targets, but hardware compilers cannot compile high-level features which are omnipresent in most advanced designs. In this thesis, the cal language is used to develop a baseline of the lar still image coder. The problem of hardware generation is later resolved using automatic transformations of the high-level features into their equivalent low-level ones. These transformations are validated using different designs
Le, Guen Benjamin. "Adaptation du contenu spatio-temporel des images pour un codage par ondelettes." Phd thesis, Université Rennes 1, 2008. http://tel.archives-ouvertes.fr/tel-00355207.
Dans cette thèse, nous proposons d'aborder le problème d'adaptativité sous un angle différent. L'idée est de déformer le contenu d'une image pour l'adapter au noyau d'ondelette séparable standard. La déformation est modélisée par un maillage déformable et le critère d'adaptation utilisé est le coût de description de l'image déformée. Une minimisation énergétique similaire à une estimation de mouvement est mise en place pour calculer les paramètres du maillage. A l'issue de cette phase d'analyse, l'image est représentée par une image déformée de moindre coût de codage et par les paramètres de déformation. Après codage, transmission et décodage de ces inforrnations, l'image d'origine peut être synthétisée en inversant la déformation. Les performances en compression de ce schéma par analyse-synthèse spatiales sont étudiées et comparées à celles de JPEG2000. Visuellement, on observe une meilleure reconstruction des contours des images avec une atténuation significative de l'effet rebond.
Conservant l'idée d'adapter le contenu des images à un noyau de décomposition fixe, nous proposons ensuite un schéma de codage par analyse-synthèse spatio-temporelles dédié à la vidéo. L'analyse prend en entrée un groupe d'images (GOF) et génère en sortie un groupe d'images déformées dont le contenu est adapté à une décomposition 3D horizontale-verticale-temporelle fixe. Le schéma est conçu de sorte qu'une seule géométrie soit estimée et transmise pour l'ensemble du GOF. Des résultats de compression sont présentés en utilisant le maillage déformable pour modéliser la géométrie et le mouvement. Bien qu'une seule géométrie soit encodée, nous montrons que son coût est trop important pour permettre une amélioration significative de la qualité visuelle par rapport à un schéma par analyse-synthèse exploitant uniquement le mouvement.
Cunat, Christophe. "Accélération matérielle pour le rendu de scènes multimédia vidéo et 3D." Phd thesis, Télécom ParisTech, 2004. http://tel.archives-ouvertes.fr/tel-00077593.
Cette thèse s'inscrit dans le cadre de la composition d'objets visuels qui peuvent être de natures différentes (séquences vidéo, images fixes, objets synthétiques 3D, etc.). Néanmoins, les puissances de calcul nécessaires afin d'effectuer cette composition demeurent prohibitives sans mise en place d'accélérateurs matériels spécialisés et deviennent critiques dans un contexte de terminal portable.
Une revue tant algorithmique qu'architecturale des différents domaines est effectuée afin de souligner à la fois les points de convergence et de différence. Ensuite, trois axes (interdépendants) de réflexions concernant les problématiques de représentation des données, d'accès aux données et d'organisation des traitements sont principalement discutés.
Ces réflexions sont alors appliquées au cas concret d'un terminal portable pour la labiophonie : application de téléphonie où le visage de l'interlocuteur est reconstruit à partir d'un maillage de triangles et d'un placage de texture. Une architecture unique d'un compositeur d'image capable de traiter indifféremment ces objets visuels est ensuite définie. Enfin, une synthèse sur une plateforme de prototypage de cet opérateur autorise une comparaison avec des solutions existantes, apparues pour la plupart au cours de cette thèse.
Mora, Elie-Gabriel. "Codage multi-vues multi-profondeur pour de nouveaux services multimédia." Thesis, Paris, ENST, 2014. http://www.theses.fr/2014ENST0007/document.
This PhD. thesis deals with improving the coding efficiency in 3D-HEVC. We propose both constrained approaches aimed towards standardization, and also more innovative approaches based on optical flow. In the constrained approaches category, we first propose a method that predicts the depth Intra modes using the ones of the texture. The inheritance is driven by a criterion measuring how much the two are expected to match. Second, we propose two simple ways to improve inter-view motion prediction in 3D-HEVC. The first adds an inter-view disparity vector candidate in the Merge list and the second modifies the derivation process of this disparity vector. Third, an inter-component tool is proposed where the link between the texture and depth quadtree structures is exploited to save both runtime and bits through a joint coding of the quadtrees. In the more innovative approaches category, we propose two methods that are based on a dense motion vector field estimation using optical flow. The first computes such a field on a reconstructed base view. It is then warped at the level of a dependent view where it is inserted as a dense candidate in the Merge list of prediction units in that view. The second method improves the view synthesis process: four fields are computed at the level of the left and right reference views using a past and a future temporal reference. These are then warped at the level of the synthesized view and corrected using an epipolar constraint. The four corresponding predictions are then blended together. Both methods bring significant coding gains which confirm the potential of such innovative solutions
Gautier, Josselin. "Un modèle d'attention visuelle dynamique pour conditions 2D et 3D ; codage de cartes de profondeur et synthèse basée inpainting pour les vidéos multi-vues." Phd thesis, Université Rennes 1, 2012. http://tel.archives-ouvertes.fr/tel-00758112.
Chen, Jiazhou. "Structure d'une image : de la réalité augmentée à la stylisation d'images." Phd thesis, Université Sciences et Technologies - Bordeaux I, 2012. http://tel.archives-ouvertes.fr/tel-00977086.
Guiard-Marigny, Thierry. "Modélisation tridimensionnelle des articulateurs de la parole : implémentation temps réel et mesures d'intelligibilité bimodale." Grenoble INPG, 1996. http://www.theses.fr/1996INPG0164.
Neyret, Fabrice. "Complexité Naturelle et Synthèse d'Images." Habilitation à diriger des recherches, 2001. http://tel.archives-ouvertes.fr/tel-00005790.