Nvidia patents method to convert compressed graphics textures for hardware use
This patent describes a method for converting a single, compressed file containing multiple surface details into separate textures that a computer's graphics chip can read directly. It uses a neural network to translate this data into a specific format supported by the hardware, ensuring the visual details of 3D objects are displayed correctly.
In the filing’s own words
In computer graphics, texture refers to a type of surface, including the material characteristics, that can be applied to an object in an image. A texture may be defined using numerous parameters, such as color(s), roughness, glossiness, etc. In some implementations, a texture may be represented as an image that can be placed on a three-dimensional (3D) model of an object to give surface details to the 3D object. To reduce a size of textures (e.g. for storage and transmission), textures in a texture set may be compressed together. The present disclosure provides for transcoding a compressed texture set to textures with a hardware-supported compression format.
What exactly they claim (claim 1)
1. A method, comprising: at a device: accessing a single texture representation of a texture set comprised of a plurality of different textures, each texture in the texture set including a plurality of parameters that define at least one property of an object surface; transcoding by at least one neural network at least a portion of the single texture representation into at least a portion of the plurality of different textures with a hardware-supported compression format; and outputting the at least a portion of the plurality of different textures with the hardware-supported compression format.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- Transcoding compressed texture sets to textures with a hardware-supported compression format
- Patent number
- US12802279B2
- Application number
- 18661448
- Filed
- May 10, 2024
- Granted
- Nov 17, 2026
- Inventors
- 12
- Claims
- 51
Classified under
G06T 9/00 Physics & computingG06T 15/005 Physics & computingG06T 15/04 Physics & computingG06V 10/44 Physics & computingH04N 19/40 Electricity & electronicsH04N 19/91 Electricity & electronicsMore 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.
