/Patent Tracker
NvidiaGranted patentAI & softwareInterest 4/10

Nvidia patents method for blending video pixels using neural networks

Nvidia describes a technique for improving video quality by combining pixels from different frames. It uses neural networks to create specific filters that determine how much each pixel contributes to the final image.

Why it mattersThis improves how computers process and enhance video, which is useful for anyone who works with digital media or video editing tools.

In the filing’s own words

Apparatuses, systems, and techniques are presented to reconstruct one or more images. In at least one embodiment, one or more anisotropic filters are used to determine one or more pixel blending weights.

What exactly they claim (claim 1)

1. One or more processors, comprising circuitry to: cause one or more neural networks to generate one or more anisotropic filters based, at least in part, on one or more video frames and one or more upsampled video frames; use the one or more neural networks to generate one or more pixel blending weights based, at least in part, on the one or more anisotropic filters; and blend two or more pixels of the one or more video frames and the one or more upsampled video frames using the one or more pixel blending weights.

Facts

Company
Nvidia (Nvidia Corporation)
Official title
Generating image blending weights
Patent number
US12749146B2
Application number
17564703
Filed
Dec 29, 2021
Granted
Sep 29, 2026
Inventors
1
Claims
33

Classified under

G06T 3/4046 Physics & computingG06T 3/18 Physics & computingG06T 3/4053 Physics & computingG06T 7/207 Physics & computingG06T 11/10 Physics & computingG06T 2207/10016 Physics & computing

More from Nvidia in AI & software

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.