System Architecture for Supporting Multiple Live Actors in Web3D Virtual Conference
Abstract. For live actors to perform as 3D models with seamless computer graphic computing, the methodology of constructing a cleaned and smooth model in real time and the design of the system architecture to support the streaming multi-model live actors are a huge challenge to be made. With the technique of semantic image segmentation applied for generating the entire human body, the 3D model needed to be built up with a segmented image as a texture. Moreover, to enable the live actor virtually intractable with others, the approach of producing the multi-actor models is required for the telecommuting system. Therefore, by the combination of the concepts above, the system with multiple live actors can be created in the purpose of making a live group conference in virtual reality with an immersive experience.