Nvidia patents AI method to build detailed 3D models from photos
Nvidia describes a system that uses one set of neural networks to create a basic 3D shape of a physical object. It then uses a second set of neural networks to run in parallel, adding different levels of fine detail to that base shape to create a more accurate final model.
In the filing’s own words
Apparatuses, systems, and techniques are presented to generate digital reconstructions of physical objects. In at least one embodiment, one or more first neural networks are used to generate a three-dimensional (3D) model having a first level of detail, and one or more second neural networks are used to modify the 3D model to have a second level of detail.
What exactly they claim (claim 1)
1. A processor, comprising one or more circuits to: cause one or more first neural networks to generate a three-dimensional (3D) model having a first level of detail; and cause a plurality of second neural networks, different from the one or more first neural networks, to generate different modified versions of the 3D model with second levels of detail that are higher than the first level of detail, wherein at least some of the second plurality of neural networks generate the different modified versions of the 3D model in parallel using different processing resources and different reconstruction techniques given the 3D model as input; and combine the respective modified versions of the 3D model to generate a modified 3D model.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- Neural network-based object reconstruction
- Patent number
- US12802348B2
- Application number
- 18212047
- Filed
- Jun 20, 2023
- Granted
- Nov 17, 2026
- Inventors
- 1
- Claims
- 24
Classified under
G06T 17/00 Physics & computingG06T 7/40 Physics & computingG06T 7/60 Physics & computingG06T 19/20 Physics & computingG06T 2207/20081 Physics & computingG06T 2207/20084 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 chip that turns text into video using noise reduction Nov 5, 2026
- Nvidia patents system that translates specific speakers in group conversations Nov 12, 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.
