Google patents video decoding that refines motion using warped models
This filing describes a method for decoding video by improving how motion between frames is predicted. It uses specific mathematical models to calculate refined motion vectors when they are not explicitly sent in the data stream, helping to reconstruct the image more accurately.
In the filing’s own words
Decoding including motion refinement using bilateral matching with a warped motion model includes decoding a current block of a current frame from an encoded bitstream by obtaining a refined prediction block for decoding the current block using bilateral matching, which includes obtaining a refinement model from available warped refinement models, wherein the available warped refinement models include a four-parameter scaling refinement model, a three-parameter scaling refinement model, and a four-parameter rotational refinement model, and obtaining refined motion vectors using the warped refinement model and previously obtained reference frame data in the absence of data expressly indicating the refined motion vectors in the encoded bitstream and generating refined prediction block data using the refined motion vectors. Decoding the current block includes generating reconstructed block data using the refined prediction block data, including the reconstructed block data in reconstructed frame data for the current frame, and outputting the reconstructed frame data.
What exactly they claim (claim 1)
1. A method comprising: generating reconstructed block data by decoding a current block of a current frame from an encoded bitstream, wherein decoding the current block includes: obtaining a refined prediction block for decoding the current block using bilateral matching, wherein obtaining the refined prediction block includes: obtaining a refinement model from available warped refinement models, wherein the available warped refinement models include a four-parameter scaling refinement model, a three-parameter scaling refinement model, and a four-parameter rotational refinement model; obtaining refined motion vectors using the warped refinement model and previously obtained reference frame data, wherein the refined motion vectors are not expressly indicated in the encoded bitstream; and generating refined prediction block data using the refined motion vectors; generating reconstructed block data using the refined prediction block data; including the reconstructed block data in reconstructed frame data for the current frame; and outputting the reconstructed frame data.
Facts
- Company
- Google (GOOGLE LLC)
- Official title
- MOTION REFINEMENT USING BILATERAL MATCHING WITH WARPED MODELS
- Publication number
- US20260281404A1
- Application number
- 19472753
- Filed
- Apr 3, 2024
- Published
- Sep 17, 2026
- Inventors
- 6
- Claims
- 20
Classified under
H04N 19/44 Electricity & electronicsH04N 19/176 Electricity & electronicsH04N 19/61 Electricity & electronicsMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.