No abstract

No abstract

Current telepresence systems, while being a great step forward in videoconferencing, still have important points to improve in what eye-contact, gaze and gesture awareness concerns. Many-to-many communications are going to greatly benefit from mature autostereoscopic 3D technology; allowing people to engage more natural remote meetings, with proper eye-contact and better spatiality feeling. For this purpose, proper real-time multi-perspective 3D video capture is necessary (often based on one or more View+Depth data sets). Given current state of the art, some sort of foreground segmentation is often necessary at the acquisition in order to generate 3D depth maps with hight enough resolution and accurate object boundaries. For this, one needs flicker-less foreground segmentations, accurate to borders, resilient to noise and foreground shade changes, and able to operate in real-time on performing architectures such as GPGPUs. This paper introduces a robust Foreground Segmentation approach used within the experimental immersive 3D Telepresence system from EU-FP7 3DPresence project. The proposed algorithm is based on a costs minimization using Hierarchical Believe Propagation and outliers reduction by regularization on oversegmented regions. The iterative nature of the approach makes it scalable in complexity, allowing it to increase accuracy and picture size capacity as GPGPUs become faster. In this work, particular care in the design of foreground and background cost models has also been taken in order to overcome limitations of previous work proposed in the literature.

In a typical desktop video-conference setup, the camera and the display screen cannot be physically aligned. This problem produces lack of eye contact and substantially degrades the user's experience. Expensive hardware Systems using semireflective materials are available on the market to solve the eye gazing problem. However, these specialized systems are far away from the mass market. This paper presents an alternative approach using stereo rigs to capture a three-dimensional model of the scene. This information is then used to generate the view from a virtual camera aligned with the conference image the user looks at.A videoconferencia permite la comunicación cara a cara de personas geográficamente distantes mediante la transmisión bidireccional de audio y vídeo. Sin embargo, la expansión de esta tecnología sigue muy por debajo de las expectativas generadas inicialmente. Superados problemas como el coste o el ancho de banda, parece que la principal barrera para una adopción generalizada de la videoconferencia es la falta de contacto visual [1]. En un entorno doméstico típico, la cámara y la pantalla no se pueden alinear físicamente, tal y como se muestra en la Fig.1. El usuario mira hacia la imagen del interlocutor remoto mostrada en el monitor, pero no directamente a la cámara desde la cual es observado, por lo que se pierde la impresión de estar mirando a los ojos del interlocutor. Se ha demostrado [3] que si el ángulo de divergencia entre la cámara y la pantalla es superior a cinco grados, la pérdida de contacto visual es apreciable. En un escenario habitual, con en usuario sentado frente al ordenador, el valor de este ángulo se sitúa entre los quince y veinte grados. Esto conlleva efectos psicológicos negativos, dado que la falta de contacto visual, o esquivar la mirada del interlocutor, tiende a asociarse con el engaño [2], por lo que por encima del umbral de divergencia, 1la