MicrosoftPatent applicationAI & softwareInterest 4/10

Microsoft patents method to feed video motion data into image models

Patent drawing
Patent drawing from the official filing.

Microsoft filed a patent application for a system that extracts motion data while decompressing a video file. It uses this data to select specific pixel regions to send to an image processing model, rather than processing the entire video frame.

Why it mattersThis technique could help software analyze video more efficiently by focusing only on moving parts of the screen.

In the filing’s own words

The present disclosure relates to systems, methods, and computer-readable media for selectively identifying pixel data to provide as an input to an image processing model based on motion data associated with the content of a digital video. For example, systems disclosed herein include receiving a compressed digital video and decompressing the compressed digital video to generate a decompressed digital video. The systems disclosed herein further include extracting or otherwise identifying motion data while decompressing the compressed digital video. The systems disclosed herein also include analyzing the motion data to determine a subset of pixel data from the decompressed digital video to provide as input to an image processing model trained to generate an output based on input pixel data.

What exactly they claim (claim 1)

1. A method, comprising: generating decompressed digital video by decompressing compressed digital video, wherein the decompressing the compressed digital video comprises: identifying motion data from the compressed digital video; and generating pixel data of a plurality of frames based at least in part on the motion data; identifying, using at least some of the motion data, plural portions of the decompressed digital video, each of the plural portions corresponding to a region of interest within one of the plurality of frames; selecting for the plural portions, based at least in part on results of the identifying the plural portions, a subset of the pixel data of the plurality of frames to provide to an image processing model; and providing, as inputs to the image processing model, the subset of the pixel data for the plural portions and at least some of the motion data, the image processing model having been trained to generate output based on pixel data input and associated motion data input.

Facts

Company
Microsoft (Microsoft Technology Licensing, LLC)
Official title
SELECTIVELY IDENTIFYING DATA BASED ON MOTION DATA FROM A DIGITAL VIDEO TO PROVIDE AS INPUT TO AN IMAGE PROCESSING MODEL
Publication number
US20260359994A1
Application number
19733471
Filed
Jul 7, 2026
Published
Nov 12, 2026
Inventors
4
Claims
20

Classified under

G06T 7/246 Physics & computingG06T 7/215 Physics & computingH04N 19/182 Electricity & electronicsH04N 19/527 Electricity & electronicsH04N 19/87 Electricity & electronicsH04N 23/6811 Electricity & electronics

More from Microsoft 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.