Qualcomm's New Patent Pulls Motion Data from Inside Its Own Diffusion Model
Qualcomm is trying to extract motion data from a diffusion model's own internal steps — not as an afterthought, but as the…
133 filings · category
AI image & video patents
Generating and remaking pictures: text-to-image, video synthesis, upscaling, and the editing tricks that redraw photos after the shutter clicks.
Recent filings
133 total
Intel Patents an AI That Teaches Robots to Imagine What's Around the Corner
Robots are usually blind to whatever their camera isn't directly pointed at — Intel's new patent uses the same AI image-filling tech…
Adobe Patents a One-Step Transformer Prior for Text-to-Image Synthesis
Adobe is patenting a shortcut in the text-to-image pipeline — a transformer-based model that converts a text prompt into an image embedding…
Adobe Patents a Split-Layer AI Relighting System for Photos
Changing the lighting in a photo after the fact sounds simple, but shadows on your subject and shadows on the background follow…
Adobe Patents a Neural Network System for Cleaner Subject-Selection Masks
Anyone who has tried to cut out a subject with multiple disconnected parts — like a person holding a fork — knows…
Google Patents a Multi-Stage AI Pipeline for Real-Time Image Restoration
Google has patented a clever iterative training method that progressively teaches smaller, faster AI models to restore degraded photos — with the…
Google Patents a Diffusion-Based System for Labeling Every Pixel in Images and Video
Google is applying the same generative AI technology behind image synthesis tools to one of computer vision's hardest problems — identifying and…
Google Patents an AI System That Builds Videos Segment by Segment from Text
Most AI video generators spit out a fixed-length clip and stop. Google's new patent describes a system that keeps going — stitching…
Meta Patents an AI Image Editor That Picks Its Own Edit Tasks From Plain-Language Instructions
Instead of asking you to pick from a menu of filters or tools, Meta's new patent describes a system that reads what…
Google Patents an AI Gatekeeper That Decides Which Photos Are Worth Enhancing
Not every blurry photo deserves the full AI treatment — and Google is patenting a system smart enough to know the difference.…
Google Patents a Mixture-of-Experts AI System for Smarter Video Compression
Google is patenting an AI-driven video compression system that uses a team of machine learning models — not just one — to…
Nvidia Patents a Diffusion AI System for Teaching Robots to Grab Objects
Getting a robot to reliably pick up an object sounds simple — it's one of the hardest unsolved problems in robotics. Nvidia…
Get the weekly Patentlyze email
We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.