The interest in immersive 3D video conference systems exists now for many years from both sides, the commercialization point of view as well as from a research perspective. Still, one of the major bottlenecks in this context is the computational complexity of the required algorithmic modules. This paper discusses this problem from a hardware point of view. We use new fast graphics board solutions, which allow high algorithmic parallelization in consumer PC environments on one hand and look at state-of-the-art powerful multi-core CPU processing capabilities on the other hand. We propose a novel scalable and high performance 3D acquisition framework for immersive 3D videoconference systems which takes benefit from both sides. In this way we are able to integrate complex computer vision algorithms, such as Visual Hull, multi-view stereo matching, segmentation, image rectification, lens distortion correction and virtual view synthesis as well as data encoding, network signaling and capturing for 16 HD cameras in one real-time framework. This paper is based on results and experiences of the European FP7 research project 3D Presence which aims to build a real-time three party and multi-user 3D videoconferencing system
In this work, a novel and fast algorithm for real-time 3D body reconstruction from stereo sequences is proposed. The main contributions of this work consist of a novel approach for a statistically guided stereo processing and a data parallel iteration scheme for 3D estimation that includes temporal predecessors from a local spatial neighborhood. A purely GPU based implementation is provided that exhibits a nearly linear scaling of the runtime with respect to the number of GPUs. This leads to an inherent sub-pixel processing due to the availability of hardware supported texture lookups. Our implementation is able to process 4K (UHD) stereo streams on a 4×4 grid with 30 fps on a single state-of-the-art consumer graphics card. The algorithmic performance of our approach is demonstrated in the context of an immersive TV application
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.