Nvidia patents image processing method using dual attention networks
Nvidia describes a method for processing images by breaking them into small sections called patches. The system uses two types of attention mechanisms to analyze how these patches relate to each other and how different color channels interact, creating a more accurate understanding of the image.
In the filing’s own words
Apparatuses, systems, and techniques to generate a robust representation of an image. In at least one embodiment, input tokens of an input image are received, and an inference about the input image is generated based on a vision transformer (ViT) system comprising at least one self-attention module to perform token mixing and a channel self-attention module to perform channel processing.
What exactly they claim (claim 1)
1. A method of operating a neural network to process an input image and from the input image generate an output image, the input image divisible into one or more patches and having a channel dimension, the method comprising: aggregating one or more feature representations of the one or more patches to obtain one or more aggregated feature representations; aggregating the one or more aggregated feature representations, at least in part by computing an attention matrix along the channel dimension to obtain one or more channel-aggregated feature representations; generating an inference about the input image based, at least in part, on the one or more channel-aggregated feature representations; and generating the output image based, at least in part, on the inference.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- ROBUST VISION TRANSFORMERS
- Publication number
- US20260268649A1
- Application number
- 19675260
- Filed
- May 12, 2026
- Published
- Sep 10, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06V 10/82 Physics & computingG06F 21/1014 Physics & computingG06V 10/30 Physics & computingG06V 10/7715 Physics & computingG06V 10/778 Physics & computingH04N 1/32336 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 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.