Waymo Patents an On-Board Vision-Language Model That Answers Questions About the Road Ahead
Waymo is patenting a system that lets different parts of a self-driving car ask a vision-language model focused questions about specific patches…
291 filings · topic
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
291 total
Samsung Patents a Real-Time Video System That Labels Every Pixel Across Frames
Imagine a camera that doesn't just detect the car in a video — it labels every single pixel in every frame, keeps…
IBM Patents a Mixture-of-Experts System for Tracing Text Back to Its Source
IBM is patenting a way to figure out where a piece of text originally came from — using a Mixture of Experts…
Adobe Patents a Single Neural Network That Runs Multiple Segmentation Tasks at Once
Cutting out a subject, isolating a sky, and detecting every person in a photo usually means running three separate AI models. Adobe's…
Adobe Patents a Machine Learning System for Reading Schematic Diagrams
Computers are great at reading words in a PDF, but terrible at understanding the circuit diagram or flowchart sitting right next to…
Adobe Patents a Complexity-Aware System for Smarter AI Inpainting
Adobe is patenting a way for its AI image-editing tools to first measure how visually complex a scene is — then automatically…
Microsoft Patents an AI System That Sorts Your Screenshots by What You Were Actually Doing
Microsoft is patenting a way to automatically slice a long stream of screenshots into discrete activity chunks — so instead of a…
X Development Files Patent for Vision-Based Blast Furnace Pellet Optimization
Google's moonshot lab X Development is filing patents in… blast furnace steelmaking? Yes, and the core idea — using computer vision to…
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…
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…
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.