/Patent Tracker
GooglePatent applicationAI & softwareInterest 2/10

Google patents video compression using predicted motion paths

This filing describes a method for compressing video files by predicting how objects move in a frame based on their movement in previous frames. Instead of sending the full movement data for every part of the video, the system sends only the difference between the predicted movement and the actual movement, which reduces the file size.

Why it mattersThis is a technical improvement to video encoding standards that helps reduce data usage for streaming and storage, though it is unlikely to be visible to end users as a distinct feature.

In the filing’s own words

Decoding using motion vector prediction with derived motion trajectory includes obtaining, from previously reconstructed reference frames available for reconstructing a current frame, reference frame motion fields data for reconstructing the current frame, obtaining, using the reference frame motion fields data, trajectory mapping data for reconstructing the current frame, accessing, from the encoded bitstream, current encoded block data for a current block of the current frame; obtaining a motion vector prediction for the current block in accordance with the trajectory mapping data, obtaining a differential motion vector from the current encoded block data, obtaining a motion vector for the current block by adding the motion vector prediction and the differential motion vector, decoding the current block using the motion vector to obtain decoded block data for the current block, and obtaining reconstructed frame data for the current frame using the decoded block data.

What exactly they claim (claim 1)

1. An apparatus comprising: a non-transitory computer-readable medium; and a processor configured to execute instructions stored on the non-transitory computer-readable medium to: generate an encoded bitstream, wherein, to generate the encoded bitstream, the processor executes the instructions to encode a current frame from an input video stream, wherein, to encode the current frame, the processor executes the instructions to: obtain, from previously reconstructed reference frames available for encoding the current frame, reference frame motion fields data for encoding the current frame; obtain, in accordance with the reference frame motion fields data, trajectory mapping data for encoding the current frame; obtain a motion vector prediction for a current block from the current frame in accordance with the trajectory mapping data; obtain current encoded block data, wherein, to obtain the current encoded block data, the processor executes the instructions to encode the current block in accordance with a current motion vector; obtain, as a differential motion vector, a result of subtraction of the motion vector prediction from the current motion vector; and include, in the encoded bitstream, current encoded block data for the current block, wherein the current encoded block data for the current block includes the differential motion vector; and output the encoded bitstream.

Facts

Company
Google (GOOGLE LLC)
Official title
MOTION VECTOR PREDICTION WITH DERIVED MOTION TRAJECTORY
Publication number
US20260270441A1
Application number
19660480
Filed
Apr 28, 2026
Published
Sep 10, 2026
Inventors
4
Claims
20

Classified under

H04N 19/139 Electricity & electronicsH04N 19/105 Electricity & electronicsH04N 19/176 Electricity & electronics

More from Google 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.