Intel Patents a Way to Help AI Pick the Best Starting Point for Video
When an AI generates a video, the random starting point it picks can mean the difference between a coherent clip and a…
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
Sony's New Patent Stops AI-Upscaled Games from Flickering Between Frames
Upscaling a single game frame is one problem. Making a hundred consecutive frames look like they belong together is a harder one.…
Google Patents a Chain of AI Steps That Turns Text Into Video
Google has patented a system that generates videos from plain text by passing the output through a chain of AI models, each…
Google Patents an AI That Writes Its Own Image Prompts to Build Ads
Google is patenting a system where AI not only generates ad images but also figures out what those images should look like…
Samsung Patents a Training Trick That Teaches AI to Restore Photos From the Background Out
Most AI photo-restoration tools treat every part of an image equally. Samsung's new patent flips that assumption, training its model on the…
Samsung Patents a Three-AI System That Builds, Titles, and Illustrates Content Lists Automatically
Samsung is patenting a system where three AI models work in sequence: one picks content, another writes a title for the picks,…
Sony Patents an AI Video Upscaler That Tracks Motion Frame by Frame
Sony is patenting a way to make low-resolution video look sharper by teaching an AI to remember where every pixel was in…
Intel Patent Boosts AI Video Upscaling Through Smarter Codec-Aware Processing
AI video upscaling looks great, but it's expensive to run on every single frame. Intel's new patent describes a system that only…
Nvidia Patents Software That Fills In Missing Image Colors Across Frames
Nvidia is patenting a way to use neural networks to figure out what color a pixel should be, not just from the…
Nvidia Files Patent for Software That Generates Images From Random Noise
Nvidia has patented a processor-level system that uses neural networks to generate images from noise values, the same core idea behind modern…
Nvidia Patents a Two-Stage Method for Teaching AI to See and Rebuild Images
Before an AI can generate a picture, it has to learn how to compress one. Nvidia's latest patent attacks that compression step…
Samsung Patents a Fix for Flickering AI Video Effects Between Frames
If you've ever seen an AI-enhanced video where the effect seems to pulse or shimmer from one frame to the next, Samsung…
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.