Nvidia patents method to speed up 3D image rendering
Nvidia describes a technique for creating new views of 3D objects by deciding exactly where to gather data points. It uses a machine learning model to map the object's features and creates a variable-thickness boundary around it, sampling only the necessary areas to build the final image.
In the filing’s own words
In various examples, images (e.g., novel views) of an object may be rendered using an optimized number of samples of a 3D representation of the object. The optimized number of the samples may be determined based at least on casting rays into a scene that includes the 3D representation of the object and/or an acceleration data structure corresponding to the object. The acceleration data structure may include features corresponding to characteristics of the object, and the features may be indicative of the number of samples to be obtained from various portions of the 3D representation of the object to render the images. In some examples, the 3D representation may be a neural radiance field that includes, as a neural output, a spatially varying kernel size predicting the characteristics of the object, and the features of the acceleration data structure may be related to the spatially varying kernel size.
What exactly they claim (claim 1)
1. A method comprising: determining, using a machine learning model, one or more characteristics associated with a three-dimensional (3D) representation of an object depicted in one or more first images; determining, based at least on the one or more characteristics, one or more offset distances for a boundary region associated with the 3D representation; generating the boundary region based at least on the one or more offset distances, the boundary region having a first thickness at a first portion of the 3D representation and a second thickness at a second portion of the 3D representation; and rendering one or more second images of the object using one or more samples of the 3D representation obtained from locations within the boundary region.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- ACCELERATED SCENE RENDERING
- Publication number
- US20260320902A1
- Application number
- 19720651
- Filed
- Jun 25, 2026
- Published
- Oct 15, 2026
- Inventors
- 9
- Claims
- 20
Classified under
G06T 15/06 Physics & computingG06V 10/44 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.