NVIDIA Research and the University of Maryland have developed QUEEN, an AI model that enables streaming of free-viewpoint video, allowing viewers to experience a 3D scene from any angle.
QUEEN can be used for immersive streaming applications, skill-based teaching, enhancing video conferencing, and teleoperating robots in industrial environments.
The model balances factors like compression rate, visual quality, encoding time, and rendering time to deliver optimized pipeline and high-quality visuals in near real-time.
QUEEN outperforms previous methods in terms of speed and visual quality, making it suitable for media broadcasts, warehouse operations, and interactive videoconferencing.