Artificial intelligence (AI) and other emerging technologies are reaching new levels of accomplishment each and every day, with no sign of plateauing in the near future. Venture Beat brought this interesting information to our attention in their article, “DeepMind AI can generate convincing photos of burgers, dogs, and butterflies.”
Now a system that can produce convincing photos out of whole cloth is the newest in image synthesis – the process of creating new images from some form of image description. This product is a result of AI, researchers at Google subsidiary DeepMind and Heriot-Watt University.
AI approximates food pics, landscapes portraits, and candid pet photos with impressive consistency. In some cases, the novel samples are almost impossible to distinguish from those taken with a camera.
When it came to training the model, the researchers sourced ImageNet, an image database maintained by Stanford and Princeton. And to confirm their design was scalable, they utilized JFT-300M, a dataset of 300 million real-world images labeled with 18K categories.
This will take photo editing and altering to an entirely new level.
Melody K. Smith
Sponsored by Access Innovations, the world leader in taxonomies, metadata, and semantic enrichment to make your content findable.