/Patent Tracker
GooglePatent applicationAI & softwareInterest 4/10

Google patents method to auto-create datasets for face expression filters

Patent drawing
Patent drawing from the official filing.

Google describes a system that automatically creates training data for photo editing effects that change facial expressions. It works by analyzing pairs of normal and expressive faces to build a mathematical 'vector' that captures the specific look of that expression, then applying it to new images to generate a large dataset. This dataset is then used to train a machine learning model that can apply the same expression effect to any input photo.

Why it mattersThis improves the efficiency of developing photo filters by automating the creation of the necessary training data, which is a routine but important step in building image editing tools.

In the filing’s own words

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatically generating datasets for a particular target expression photo effect. In one aspect, a system comprises receiving a plurality of image pairs, each comprising an original face image and an expressive face image representative of a target expression photo editing effect, generating an initial overall editing vector, wherein generating the initial overall editing vector comprises processing each image pair using a style space encoder model to generate an embedding of the original face image and an embedding of the expressive face image in an embedding space, optimizing the initial overall editing vector in accordance with one or more optimization criteria to generate an optimized overall editing vector, and applying the optimized overall editing vector to an input face image to generate a target expression face image that has the target expression photo editing effect.

What exactly they claim (claim 1)

1. A computer-implemented method comprising: obtaining an optimized overall editing vector representing a target expression photo editing effect, wherein the optimized editing vector has been optimized in accordance with one or more optimization criteria in an embedded style space; generating a target expression dataset comprising a plurality of target expression face images by applying the optimized editing vector to embeddings of a plurality of input face images; training, using the target expression dataset, a machine learning model to process an input image and generate an output image having the target expression photo editing effect; and providing the trained machine learning model for deployment.

Facts

Company
Google (Google LLC)
Official title
OPTIMIZATION OF OVERALL EDITING VECTOR TO ACHIEVE TARGET EXPRESSION PHOTO EDITING EFFECT
Publication number
US20260301464A1
Application number
19709780
Filed
Jun 16, 2026
Published
Oct 1, 2026
Inventors
3
Claims
20

Classified under

G06V 40/174 Physics & computingG06T 7/0002 Physics & computingG06T 11/60 Physics & computingG06V 10/774 Physics & computingG06V 10/82 Physics & computingG06V 40/168 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

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.