Google secures grants for image enhancement and video stabilization while publishing new AI image and video generation applications.
The filing
On November 10, 2026, Google LLC received five US patents covering image enhancement via iterative machine learning, video stabilization using machine learning models, and systems for signaling user position deviations during video conferences. The company also published a European application on November 11, 2026, for an AI model that generates new images by optimizing a loss function to create structured representations of digital components (EP4838474A2 (opens in a new tab)). A cluster of US applications published on November 12, 2026, describes photo relighting, real-time text translation through inpainting, color matching in augmented reality, and bidirectional image-to-video generation (USPTO 20260359936A1 (opens in a new tab), USPTO 20260359953A1 (opens in a new tab), USPTO 20260360015A1 (opens in a new tab), USPTO 20260360030A1 (opens in a new tab), USPTO 20260360049A1 (opens in a new tab), USPTO 20260360054A1 (opens in a new tab), USPTO 20260360090A1 (opens in a new tab)).
This filing’s full text wasn’t read for this issue, so its claims and the applicant’s background aren’t shown. Both are in the record, under Sources.