Nvidia unveiled its newest AI breakthrough in the form of a mind-blowing computer vision technique that can 'paint' parts of an image that have been deleted or modified.
This is something you have to see to believe:
The Nvidia researchers explain the difference between its novel methods for painting in images with deep learning and currently existing tech in a white paper published earlier this week:
"Previous deep learning approaches have focused on rectangular regions located around the centre of the image, and often rely on expensive post-processing. The goal of this work is to propose a model for image inpainting that operates robustly on irregular hole patterns, and produces semantically meaningful predictions that incorporate smoothly with the rest of the image without the need for any additional post-processing or blending operation."
As you can see in the video above, Nvidia's technology does not suffer from the same problem as current market techniques for filling in missing spaces in images. According to the researchers, they’re the first to successfully train a neural network to process irregularly shaped holes in images.
The AI program does, almost instantly, what could take a seasoned graphic designers' minutes or even hours to accomplish.
The way it works is it uses a deep neural network to create masks and partial convolutional predictions – in essence, it creates an invisible layer that it manipulates until it 'feels' as though the image is complete.
There will be a pretty good chance that, within a couple of years, the only way to tell the difference between AI-generated imagery and ‘real’ pictures will be checking the digital signature or having individual pixels evaluated by a computer.