Apple received 1 granted patent in the VR & AR category.
The patent covers AI-powered image reprojection technology for AR/VR applications, using deep learning to predict and reconstruct frames. This approach reduces rendering costs in devices like Vision Pro and future headsets by intelligently generating visual content.
Apple's single VR & AR patent tackles the computational challenge of rendering high-quality visuals in real-time for AR and VR headsets. The system uses deep learning models constrained to only consider past and present frame data, predicting and reconstructing future frames without introducing visual artifacts that could break immersion. This temporal supersampling technique differs from traditional upscaling methods by accounting for the unique demands of head-tracked displays, where even minor latency can cause discomfort. By offloading rendering work to AI-driven prediction, the approach reduces the computational burden on Graphics processors while maintaining the responsiveness required for extended reality experiences.
All data sourced from USPTO patent filings. Google Patents may take several weeks to index recent publications. If a link is unavailable, search for the patent number at USPTO Patent Public Search.