Nvidia Patents a Two-Stage AI Pipeline for Teaching Robots to Grab Objects
Getting a robot to reliably pick up an arbitrary object is one of the hardest unsolved problems in robotics — and Nvidia…
199 filings · category
AI vision patents
Teaching machines to see: object recognition, gesture and gaze tracking, and the perception stack behind cameras, cars, and headsets. Every vision filing, decoded.
Recent filings
199 total
Microsoft Patents a Unified Contrastive Learning System for Vision AI
Training a computer vision model that's good at *everything* — object detection, image captioning, visual search — usually means training many separate…
Google Patents a Machine Learning System for Smarter Image Inpainting
Google is patenting a more principled way to train AI models that remove unwanted objects from photos — the kind of 'erase…
Nvidia Patents a System for Writing Captions About Specific Parts of an Image
Describing a whole photo is one thing — but describing exactly what's happening inside a specific bounding box, while still 'knowing' the…
Nvidia Patents an AI System That Learns Where Objects Belong Before Placing Them
Dropping a new object into a photo sounds simple — until the AI places a car on the ceiling. Nvidia's new patent…
Microsoft Patents an Automatic Quality Filter for Medical Imaging AI
Garbage in, garbage out — and in medical AI, garbage can mean a model that misses tumors. Microsoft has patented a system…
Microsoft Patents an AI System That Reads Your Audience During Video Calls
Imagine getting a live dashboard during your presentation showing which slides landed flat and which made the VP in row three nod…
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.