Nvidia Patents a Neural Network System That Compresses Video by Reading Images at Two Depths
Nvidia is patenting a video compression approach where neural networks analyze each frame twice — once for big-picture content, once for fine…
The Big Tech patents worth knowing in ai/ml, in plain English. Updated weekly from new USPTO publications.
Nvidia is patenting a video compression approach where neural networks analyze each frame twice — once for big-picture content, once for fine…
Most AI systems are locked to a specific chip once they start running. Nvidia is patenting a way to shuffle pieces of…
Nvidia is teaching an AI to look at a flat photo — the kind you take with any camera — and reconstruct…
What if your cloud infrastructure could see a traffic spike coming and spin up extra servers before users even notice a slowdown?…
Nvidia has filed a patent for a training approach that breaks images into tiles, runs each tile through multiple specialized AI vision…
Training an AI to recognize and outline objects in photos normally requires thousands of hours of humans manually tracing those objects. Nvidia's…
Getting a computer-generated car or pedestrian to look like it genuinely belongs in a real photograph is harder than it sounds —…
Nvidia is patenting a way to generate video that stays visually consistent frame-to-frame — by training neural networks on 3D point clouds,…
Every time an AI chatbot answers a question it's already answered before, it's burning computing power needlessly. Amazon's new patent describes a…
AI models are packed with numbers that are literally zero — and Amazon wants its chips to stop wasting memory and time…
Most AI image safety filters work like a sledgehammer — block enough and you avoid bad outputs, but you also wreck perfectly…
Amazon is patenting a pipeline that takes a plain-text request — like 'make a video about a dog chasing a ball in…
We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.