Patent Uses AI to Shrink Video File Sizes by Predicting Frame Changes
Compressing video without losing quality is one of the hardest problems in media tech. Microsoft's latest patent describes an AI system that…
Generating and remaking pictures: text-to-image, video synthesis, upscaling, and the editing tricks that redraw photos after the shutter clicks.
Compressing video without losing quality is one of the hardest problems in media tech. Microsoft's latest patent describes an AI system that…
What if your car's parking camera could show you an angle it doesn't actually have a lens for? Nvidia is patenting a…
When an AI tries to understand an image, it often works with a shrunken-down version first and then has to guess at…
Typing a good AI image prompt is harder than it looks. Adobe is patenting a system that fixes your prompt for you…
What if you could take a photo of a half-eaten apple and ask your phone to show you what it looked like…
Instead of typing a text prompt to edit a photo with AI, Samsung's patent describes a system that reads your image, pulls…
Generating video with AI is computationally brutal, especially on a phone chip. Qualcomm's latest patent describes a way to process only the…
Generating an image with today's AI tools can require dozens of processing steps under the hood. Nvidia is patenting a training method…
Training a robot to recognize objects normally requires thousands of real photos, taken in every possible lighting condition and angle. Nvidia's new…
Every time an AI image model generates a picture, it repeats many of the same calculations over and over. Google's new patent…
Instead of generating an image from scratch, Microsoft's patented system first searches the web for real examples of what you asked for,…
Finding defects on a production line is only as good as your training data. Samsung's new patent tackles a core frustration in…
We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.