Cesar Tadeu Pozzer

Automatic Dynamic Task Distribution between CPU and GPU for Real-Time Systems

The increase of computational power of programmable GPU (graphics processing unit) brings new concepts for using these devices for generic processing. Hence, with the use of the CPU and the GPU for data processing come new ideas that deals with distribution of tasks among CPU and GPU, such as automatic distribution. The importance of the automatic distribution of tasks between CPU and GPU lies in three facts. First, automatic task distribution enables the applications to use the best of both processors. Second, the developer does not have to decide which processor will do the work, allowing the automatic task distribution system to choose the best option for the moment. And third, sometimes, the application can be slowed down by other processes if the CPU or GPU is already overloaded. Based on these facts, this paper presents new schemes for efficient automatic task distribution between CPU and GPU. This paper also includes tests and results of implementing those schemes with a test case and with a real-time system.

Automatic Video Editing for Video-Based Interactive Storytelling

The development of interactive narratives with the quality of feature films is the central challenge of what we can name Video-Based Interactive Storytelling. A promising approach to this question is the use of prerecorded videos with real actors. Amongst several technical challenges, this approach firstly requires automatic video editing methods for interactive narratives. However, this is a critical issue not fully covered in the literature. In this paper, we present a real-time editing method for interactive storytelling systems, which automatically generates the most adequate shot transitions, swaps video segments to avoid jump cuts, and creates adequate looping scenes. Moreover, these features consider the characteristics of the ongoing story.

Non-branching Interactive Comics

Comics are a unique and classical form of storytelling. The advent of interactive narratives brings the possibility of interaction to the traditional comic books. In this paper we present a non-branching interactive comics system capable of generating dynamic interactive narratives in the format of comic books. The system allows users to interact with certain objects, and then observe the consequences of their actions in the unfolding story. We validate the proposed system with a user study conducted with 18 participants. The results indicate that such systems may indeed provide an attractive form of entertainment.

Planning and Interaction Levels for TV Storytelling

Interactivity, coherence and diversity of the stories are key issues for the development of interactive storytelling systems. When stories are to be told via interactive TV, special interaction methods are also necessary in order to cope with high responsiveness requirements. In this paper, we describe the extension of the interactive storytelling system Logtell we have developed to run in an interactive TV environment. Planning algorithms have been applied to provide coherence and diversity for the stories at levels of both plot composition and dramatization. A new architecture was designed to combine these algorithms with special interaction methods incorporated to achieve high responsiveness.

Virtual cinematography director for interactive storytelling

This paper proposes an intelligent cinematography director for plot-based storytelling systems. The role of the director is to select in real-time the camera shots that best fit for the scenes and present the content in an interesting and coherent manner. Directors knowledge is represented with a collection of support vector machines (SVM) trained to solve cinematography problems of shot selection. With this work we introduce the use of support vector machines, applied as an artificial intelligence method, in a storytelling director. This approach also can be extended and applied in games and other digital entertainment applications.

Conciliating coherence and high responsiveness in interactive storytelling

Interactive storytelling is a new form of digital entertainment that brings together techniques and tools for the creation, visualization and control of interactive stories through electronic means. One of the main challenges of interactive storytelling is the generation of stories that are both coherent and interesting, while providing means to allow the user to interact with the story. On the other hand, users intervention should not violate the rules of the chosen genre, leading to unlikely developments. Another problem arises when storytelling environments require high responsiveness, as is the case in interactive TV. The fact that storytelling systems are usually very CPU intensive should not affect responsiveness. This paper describes a model to deal with these requirements, which has been implemented over a previous version of Logtell, a logic-based tool for interactive generation and dramatization of stories.

Draw your own story: Paper and pencil interactive storytelling☆

Abstract Drawing is a primary human skill that has been used for thousands of years as a visual complement to written and oral storytelling. The advent of interactive narratives brings the possibility of interaction to the traditional stories. In this paper, we present a storytelling system able to dramatize interactive narratives in augmented reality over a conventional sheet of paper. The system allows users to freely interact with virtual characters by sketching objects on the paper. Users interacting with the system can thus indirectly affect the characters’ decisions, even to the point of radically subverting the storyline. We validate the proposed system with a user study conducted with 21 participants. The results show that the use of hand drawings as a form of interaction improves user satisfaction and experience and the system usability.

Multimodal, Multi-user and Adaptive Interaction for Interactive Storytelling Applications

The ability that users have to interact and change stories according to their own desires is what differentiates interactive narratives from conventional films. Moreover, this ability expands the boundaries of computer games towards new forms of digital entertainment. However, designing an interaction model for an interactive storytelling system involves several challenges, from the need for natural interaction interfaces to adequate multi-user settings. In this paper we present the development and evaluation of a multimodal, multi-user, and adaptive interaction system for an interactive storytelling application.

Neuronal editor agent for scene cutting in game cinematography

Cinematography techniques in games aim to provide high-level abstractions for operating a virtual camera on the basis of concepts borrowed from the movie industry, such as scene, shot, and line of action, among others. One typical approach is the development of agents to execute tasks that are similar to their counterparts in a real movie set: director, editor, and cinematographer. However, a game is an interactive application and resembles a live TV show or a live sport transmission, where the actions taken by all the actors are not known previously. In such a scenario, the role of the editor is of great importance, since he or she is the one who ultimately decides what point of view should appear on the screen. In the context of game cinematography, most previous work has proposed ways of mapping scene concepts and automatically controlling the virtual camera, but without paying much attention to the role of an editor agent. Our article demonstrates an intelligent editor agent that uses neuronal network classifiers to decide shot transition and has an intuitive user interface to the learning mechanism.

A Model for Interactive TV Storytelling

Interactive storytelling systems are applications to generate and dramatize interactive stories. The main challenge to such systems is the generation of coherent stories while users are watching and interfering with what is happening. In an interactive TV environment, quality and diversity of narratives are crucially important objectives. In addition, new requirements related to comfort in user interaction, responsiveness and scalability have to be taken into account. In this paper, we present a model for interactive TV storytelling to cope with these requirements. The model was implemented in a new version of the planning-based interactive storytelling system Logtell.