Forgot your password?

Enter the email address for your account and we'll send you a verification to reset your password.

Your email address
Your new password
Cancel
Earlier, the AI tech company NVIDIA wowed the world with their computer generated, hyperrealistic portraits of non-existent humans and now they are back with new Ai software. AI GauGAN, named for the post-impressionist painter is an interactive app that can turn your “rough doodles into photorealistic masterpieces with breathtaking ease.”

NVIDIA writes “GauGAN can transform your piece in a matter of seconds. The tool leverages generative adversarial networks, or GANs, to convert segmentation maps into lifelike images.” This technology may sound like just a fun art tool but the researchers write it could be a powerful tool in many creative fields.

The vice president of applied deep learning research at NVIDIA, Bryan Catanzaro has compared GauGAN’s technology to a “smart paintbrush”. It has the ability to fill details with rough segmentation maps. Technology like this, the company writes, could be highly useful for architects, urban planners, landscape designers, and even game developers. “With an AI that understands how the real world looks, professionals can better prototype ideas and make rapid changes to a synthetic scene.” Catanzaro further explained, “It’s much easier to brainstorm designs with simple sketches, and this technology is able to convert sketches into highly realistic images.”

On the surface, GauGAN is simple technology. The user draws a segmentation map, manipulates the scene, labeling segments of the image with words like ‘sky’ or ‘snow.’ This AI is trained with millions of images and is able to then fill in the elements the user has labeled in a hyperrealistic form. If the user changes the label say from ‘snow’ to ‘sea’ the entire image will transform. “It’s like a coloring book picture that describes where a tree is, where the sun is, where the sky is,” “And then the neural network is able to fill in all of the detail and texture, and the reflections, shadows, and colors, based on what it has learned about real images,” Catanzaro said.

For more interesting stories, Download the Lopscoop application from Google play store and earn extra money by sharing it on social media.

<iframe width="100%" height="250" src="https://www.youtube.com/embed/VsnzJMlMrPY" frameborder="0" allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
YOUR REACTION
  • 0
  • 0
  • 0
  • 0
  • 0
  • 0

Add you Response

  • Please add your comment.