Le contrôle de caméra virtuelle est aujourd'hui un composant essentiel dans beaucoup d'applications d'infographie. Malgré cette importance, les approches actuelles restent limitées en terme d'expressivité, d'interactivité et de performances. Typiquement, les éléments de style ou de genre cinématographique sont difficiles à modéliser et à simuler dû à l'incapacité des systèmes actuels de calculer simultanément des points de vues, des trajectoires et d'effectuer le montage. Deuxièmement, elles n'explorent pas assez le potentiel créatif offert par le couplage potentiel d'un humain et d'un système intelligent pour assister les utilisateurs dans une tâche complexe de construction de séquences cinématographiques. Enfin, la plupart des approches existantes se basent sur des techniques d'optimisation dans un espace de recherche 6D, qui s'avèrent coûteuses et donc inadaptées à un contexte interactif. Dans cette thèse, nous proposons tout d'abord un cadre unique intégrant les quatre aspects clés de la cinématographie (le calcul de point de vue, la planification de trajectoires, le montage et la visibilité). Ce cadre expressif permet de simuler certaines dimensions de style cinématographique. Nous proposons ensuite une méthodologie permettant de combiner les capacités d'un système automatique avec une interaction utilisateur. Enfin, nous présentons un modèle de contrôle de caméra efficace qui réduit l'espace de recherche de 6D à 3D. Ce modèle a le potentiel pour remplacer un certain nombre de formulations existantes. / Virtual camera control is nowadays an essential component in many computer graphics applications. Despite its importance, current approaches remain limited in their expressiveness, interactive nature and performances. Typically, elements of directorial style and genre cannot be easily modeled nor simulated due to the lack of simultaneous control in viewpoint computation, camera path planning and editing. Second, there is a lack in exploring the creative potential behind the coupling of a human with an intelligent system to assist users in the complex task of designing cinematographic sequences. Finally, most techniques are based on computationally expensive optimization techniques performed in a 6D search space, which prevents their application to real-time contexts. In this thesis, we first propose a unifying approach which handles four key aspects of cinematography (viewpoint computation, camera path planning, editing and visibility computation) in an expressive model which accounts for some elements of directorial style. We then propose a workflow allowing to combine automated intelligence with user interaction. We finally present a novel and efficient approach to virtual camera control which reduces the search space from 6D to 3D and has the potential to replace a number of existing formulations.

Le contrôle automatique de caméra est un composant essentiel en cinématographie virtuelle à la fois pour la sélection des points de vue appropriés dans une scène 3D ou pour passer en revue efficacement le contenu d'un environnement 3D. Les applications de cinématographie virtuelle reposent sur des critères réalisme afin de provoquer un impact positif chez le spectateur. Dans cette thèse, nous présentons deux contributions. Tout d'abord, nous proposons une métrique permettant d'évaluer et de corriger l'équilibre visuel dans les images basée sur un large éventail de caractéristiques visuelles, dont la taille, la silhouette, la position et la saillance d'objets cibles, associés à des métriques liées aux positions et orientations des objets. Le procédé consiste à annoter des images bien équilibrées, pour estimer automatiquement la façon dont chaque caractéristique influence l'équilibre visuel dans chaque image. Nous proposons de créer une base de données d'images annotées de façon à (i) évaluer l'équilibre dans une nouvelle image en comparant ses caractéristiques visuelles à celles de la base de donnée, et (ii) d'optimiser automatiquement les points de vue dans une scène 3D de façon à recréer un équilibre visuel. Deuxièmement, nous présentons les Camera Motion Graph, une technique pour générer facilement et efficacement des séquences cinématographiques en temps réel dans des environnements 3D dynamiques. Un Camera Motion Graph est composé de (i) morceaux de trajectoires de caméra réelles exprimées dans le repère local d'une ou plusieurs cibles, (ii) de transitions continues entre les trajectoires des caméras et (iii) de transitions représentant des sauts directs d'une trajectoire à une autre. Les échantillons de trajectoires sont construits en extrayant des mouvements de caméra à partir de véritables films en utilisant des techniques de vision par ordinateur, ou par capture de mouvement en utilisant un système de caméra virtuelle. Une transformation est proposée afin d'exprimer les trajectoires des caméras dans une représentation normalisée. Le Camera Motion Graph est alors construit par échantillonnage de toutes les paires de trajectoires de caméras et le calcul des possibilités de transitions continues ou directes. Les résultats que nous présentons illustrent la simplicité de la technique, son adaptabilité à différents environnements 3D ainsi que son efficacité. / Automated camera control techniques are key components of virtual cinematography systems by providing means to select appropriate viewpoints in a 3D scene and to efficiently review the content of a 3D environment. In this work we present two contributions. First, we propose an example-driven on-screen balance metric which estimates how well balanced is the composition of a shot. Our metric accounts for a large set of visual features including size, silhouette, position and saliency of target objects, together with metrics related to character’s positions, orientations and gaze. The process consists in annotating well balanced images, to estimate automatically how each visual feature influences balance in each image. We then rely on this database of annotated images to (i) estimate how well new images are balanced by comparing their visual features, and (ii) automatically optimize viewpoints in a 3D scene to enforce balance. Second, we present Camera Motion Graphs, a technique to easily and efficiently generate cinematographic sequences in real-time dynamic 3D environments. A camera motion graph consists of (i) pieces of original camera trajectories attached to one or multiple targets, (ii) generated continuous transitions between camera trajectories and (iii) transitions representing cuts between camera trajectories. Pieces of original camera trajectories are built by extracting camera motions from real movies using vision-based techniques, or relying on motion capture techniques using a virtual camera system. A transformation is proposed to recompute all the camera trajectories in a normalized representation, making camera paths easily adaptable to new 3D environments through a specific retargeting technique. The camera motion graph is then constructed by sampling all pairs of camera trajectories and evaluating the possibility and quality of continuous or cut transitions. Results illustrate the simplicity of the technique, its adaptability to different 3D environments and its efficiency.

Virtual camera control is nowadays an essential component in many computer graphics applications. Despite its importance, current approaches remain limited in their expressiveness, interactive nature and performances. Typically, elements of directorial style and genre cannot be easily modeled nor simulated due to the lack of simultaneous control in viewpoint computation, camera path planning and editing. Second, there is a lack in exploring the creative potential behind the coupling of a human with an intelligent system to assist users in the complex task of designing cinematographic sequences. Finally, most techniques are based on computationally expensive optimization techniques performed in a 6D search space, which prevents their application to real-time contexts. In this thesis, we first propose a unifying approach which handles four key aspects of cinematography (viewpoint computation, camera path planning, editing and visibility computation) in an expressive model which accounts for some elements of directorial style. We then propose a workflow allowing to combine automated intelligence with user interaction. We finally present a novel and efficient approach to virtual camera control which reduces the search space from 6D to 3D and has the potential to replace a number of existing formulations.

Users sharing their experiences on social media and streaming sites becomes increasingly important for marketing games. Virtual reality has the added challenge that the head movement is sometimes too erratic to capture and present on a flat screen. This paper solves this issue by automatically generating highlight cinematics for virtual reality action games using new camera angles to create easily shareable media focusing on non-players. The problem is solved by first identifying the interest over time, then split it into sequences of coherent action. The most interesting sequences are selected for the highlight reel where each sequence is split into clips tied to a specific camera angle. The highlight cinematics was evaluated using a survey. The results suggest that dynamic cameras are more engaging and interesting than static cameras. The selection of camera angles gave more significant results than the length of the highlight or the intensity of the action, pointing towards the presentation of the highlight cinematic being more important than the actual highlighted material for non-players. / Det blir alltmer viktigt att spelare delar med sig av sina upplevelser på sociala medier som en form av marknadsföring för spel. Denna delning blir svårare från virtuell verklighet till vanliga skärmar då de snabba huvudrörelserna gör det svårt att följa vad som händer. Detta problem kan lösas genom att automatiskt identifiera höjdpunkter i spel och filma in dem med nya kameravinklar för att generera en video som är enkelt delbar. Höjdpunkterna identifieras genom att först analysera intresset över tid i matchen. Därefter delas det upp i olika sekvenser där de mest intressanta sekvenserna gör upp videon. Sekvenserna delas upp i olika klipp där varje klipp är kopplat till en kameravinkel. Programmet utvärderades med en enkät där målgruppen var de som inte spelat spelet tidigare. Resultatet tyder på att dynamiska kameravinklar ses som mer engagerande och intressanta än statiska kameravinklar. Valet av kameravinklar gav mer betydande resultat än längden på videorna och intensiteten i handlingen, vilket tyder på att framläggandet av videorna är viktigare än det underliggande materialet för de som inte spelat spelet tidigare.

電影是門用畫面說故事的藝術，除了劇情上的編排，導演也必須思考如何運用鏡頭配置和運鏡技巧來渲染氣氛並傳達故事。電影拍攝製作上一直都是件費時費力的工程，儘管現在有不少電影後製工具，但專注在根據電影內容提升或改善拍攝手法的工具卻不多。本研究目標為開發智慧型電腦動畫攝影編輯輔助系統及互動操作平台，透過圖示化攝影機拍攝的結果作為選項的介面和推薦系統，讓使用者可以快速簡單的設置虛擬攝影機，配合智慧型回饋提醒系統檢查各鏡頭間是否違反拍攝規則，以達到輔助攝影初學者的目的，提供創新有效的動畫電影拍攝輔助工具。我們透過實驗讓不同攝影背景經驗的使用者操作，以驗證我們系統的可用性。 / Movie is the art of "storytelling." In addition to arranging story elements in a movie, a di-rector must also consider how to present the story by shots arrangement and operations. Filmmaking is a time-consuming process. Although there are many post-production tools available in the market, it is rare to find a tool focusing on facilitating shot arrangement to improve the quality of a movie. In this work, we have developed an intelligent camera editing system for computer animation, in which users can easily set up virtual cameras through se-lecting shot icons recommended by the system. It can also provide intelligent feedbacks to novice users and check if the shots selected by the users violate the rules in virtual cinema-tography. In order to show that the system is an innovative and effective tool for making an animation film, we have conducted an evaluation study by inviting participants with different photographic backgrounds to experience the system and verify the usability of our system.

[pt] A geração de representações visuais envolventes para storytelling interativo é um dos desafios-chave para a evolução e popularização das narrativas interativas. Usualmente, sistemas de storytelling interativo utilizam computação gráfica para representar os mundos virtuais das histórias, o que facilita a geração dinâmica de conteúdos visuais. Embora animação tridimensional seja um poderoso meio para contar histórias, filmes com atores reais continuam atraindo mais atenção do público em geral. Além disso, apesar dos recentes progressos em renderização gráfica e da ampla aceitação de animação 3D em filmes, a qualidade visual do vídeo continua sendo muito superior aos gráficos gerados computacionalmente em tempo real. Na presente tese propomos uma nova abordagem para criar narrativas interativas mais envolventes, denominada Storytelling Interativo Baseado em Vídeo, onde os personagens e ambientes virtuais são substituídos por atores e cenários reais, sem perder a estrutura lógica da narrativa. Este trabalho apresenta um modelo geral para sistemas de storytelling interativo baseados em vídeo, incluindo os aspectos autorais das fases de produção e os aspectos técnicos dos algoritmos responsáveis pela geração em tempo real de narrativas interativas usando técnicas de composição de vídeo. / [en] The generation of engaging visual representations for interactive storytelling represents a key challenge for the evolution and popularization of interactive narratives. Usually, interactive storytelling systems adopt computer graphics to represent the virtual story worlds, which facilitates the dynamic generation of visual content. Although animation is a powerful storytelling medium, live-action films still attract more attention from the general public. In addition, despite the recent progress in graphics rendering and the wide-scale acceptance of 3D animation in films, the visual quality of video is still far superior to that of real-time generated computer graphics. In the present thesis, we propose a new approach to create more engaging interactive narratives, denominated Video-Based Interactive Storytelling, where characters and virtual environments are replaced by real actors and settings, without losing the logical structure of the narrative. This work presents a general model for interactive storytelling systems that are based on video, including the authorial aspects of the production phases, and the technical aspects of the algorithms responsible for the real-time generation of interactive narratives using video compositing techniques.