NVIDIA had 276 patents in artificial intelligence during Q2 2024. NVIDIA Corp’s patents in Q2 2024 focus on various innovative systems and methods, including rendering complex surfaces with neural signed distance functions, determining associations between objects in sensor data using neural network models, generating digital representations of environments with accurate object models, estimating object poses for collision-free motion, and enhancing audio through machine learning-based super-resolution processing. These patents showcase NVIDIA’s commitment to advancing technology in multiple domains such as graphics rendering, autonomous systems, object recognition, and audio processing. GlobalData’s report on NVIDIA gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
NVIDIA had no grants in artificial intelligence as a theme in Q2 2024.
Recent Patents
Application: Real-time rendering with implicit shapes (Patent ID: US20240212261A1)
The patent filed by NVIDIA Corp. describes systems and methods for rendering complex surfaces or geometry using neural signed distance functions (SDFs) to efficiently capture multiple levels of detail (LODs) and reconstruct multi-dimensional geometry with high image quality. The architecture can represent complex shapes in a compressed format with high visual fidelity and generalize across different geometries from a single learned example. The use of extremely small multi-layer perceptrons (MHLPs) with an octree-based feature representation for the learned neural SDFs is highlighted in the patent.
The claims in the patent outline a computer-implemented method and system for rendering surfaces based on complexity thresholds or criteria, dividing surfaces into patches, determining surface patch representations using neural networks, and rendering the surface accordingly. The method includes determining complexity based on size, shape, or variation, adapting to changing complexities over time, and specifying preset complexities for surfaces. The system can be used for simulation operations, testing autonomous machine applications, rendering graphical output, deep learning operations, edge devices, Virtual Machines (VMs), data centers, or cloud computing resources. Additionally, a processor is described to render surfaces using decoded surface patch representations generated by neural networks based on surface complexity criteria, with the ability to compute neural signed distance functions (SDFs) and adapt to changing complexities over time.
To know more about GlobalData’s detailed insights on NVIDIA, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
