INVITE: 3D-Augmented Interactive Video Teleconferencing
نویسندگان
چکیده
We propose a novel approach to mixed-reality teleconferencing that focuses on 3D augmentations of multi-camera 2D video streams. We exchange information about the geometric layout of all participating meeting sites, as well as the camera parameters for surveying these spaces. We can then correctly overlay 3D graphics on top of the video feeds, representing meeting content as well as highlight annotations and interaction tools for scene manipulation and bookkeeping of meeting contributions and decisions. Our primary contribution is a standard for the delivery and interaction with such data, which will allow for immersive meeting participation on a diverse set of devices, ranging from special-purpose 3D immersive environments to ultra-mobile platforms, such as cell phones and portable video players.
منابع مشابه
Creating Adaptive Views for Group Video Teleconferencing – An Image-Based Approach
We present a system and techniques for synthesizing views for many-to-many video teleconferencing. Instead of replicating oneto-one systems for each pair of users, or performing complex 3D scene acquisition, we rely upon user tolerance for soft discontinuities for our rendering techniques. Furthermore, we observed that the participants’ eyes usually remain at a constant height (sitting height) ...
متن کاملVirtual 3D Interactions between 2D Real Multi-Views
In this paper, we introduce an image processing tool, Video Spatialization, as a new approach to navigate through a “virtualized” scene, only known by a limited set of 2D uncalibrated images (i.e without any 3D CAD model). We develop this approach in the context of an interactive application: a multipoint teleconferencing system for very low bit rate links (internet, mobile communications), bas...
متن کاملVirtual 3 D Interactions between 2 D Real Multi - Views Katia
In this paper, we introduce an image processing tool, Video Spatialization, as a new approach to navigate through a “virtualized” scene, only known by a limited set of 2D uncalibrated images (i.e without any 3D CAD model). We develop this approach in the context of an interactive application: a multipoint teleconferencing system for very low bit rate links (internet, mobile communications), bas...
متن کاملCombining Approximate Geometry with View-Dependent Texture Mapping - A Hybrid Approach to 3D Video Teleconferencing
We present a hybrid system using computer vision and graphics methods that effectively combines fast automatic 3D model extraction with view-dependent texture mapping for the purpose of real-time person-toperson 3D video teleconferencing. In our approach the problem of creating a dense disparity map is bypassed. We compute only a sparse geometric model, which is textured from multiple cameras u...
متن کاملModel-based Video Coding with Generic 2d and 3d Models
3D extraction from video gives a representation adapted to low bitrate coding and provides enhanced functionalities such as 3D cues for augmented reality and interactive navigation in photorealistic environments. But for degenerated motions of camera, like pure rotation, 3D information can not be retrieved. In this article we propose an original representation based on a hybrid 2D/3D models str...
متن کامل