Nvidia introduces GauGAN to turn sketches into realistic landscapes
Category: #tech  By Nikita Chaurasia  Date: 2019-03-20
  • share
  • Twitter
  • Facebook
  • LinkedIn

Nvidia introduces GauGAN to turn sketches into realistic landscapes

The program can blend hundreds of thousands of objects and their connection to other objects in the real world

Nvidia Research has recently introduced a generative adversarial AI system named GauGAN that allows one to create photorealistic landscapes in seconds. The neural network of GauGAN has been trained with 1 million open source Flickr images and can comprehend the relationship among more than 180 objects like water, snow, flowers, tree, bushes, mountains or hills.

The company revealed that this program can blend hundreds of thousands of objects and their connection to other objects in the real world. GauGAN is apparently just one of the advanced reality-bending AI systems from Nvidia, producer of deepfake tech which can produce realistic images of people who never existed.

With the help of this system, the user can create the shape of a tree with the usage of input tools and it will create a realistic tree. Make a straight line it will create a plain trunk. Also, a tree next to a water source will display a reflection and when there is a change in season, snow would cover the ground and tree will be without leaves.

Reliable sources mentioned that GauGAN creates results that are unique and impressive. With this software, style transfer can also be possible so that an image can show the cooler lights of a city’s skyline or adopt a warm sunset glow.

GauGAN is supposedly a multimodal system, meaning that if two users produce the same sketch with the exact setting, it will ensure that the software creates different results with the random numbers built into the projects.

Sources informed that in order to create real time results, GauGAN has to run on a Tensor computing platform and Nvidia displayed the software on an RDX Titan GPU platform. According to Bryan Catanzaro, VP of Applied Deep Learning Research reported that with some alternations, GauGAN can run efficiently on any platform, including CPUs.

GauGAN builds from the learnings of Pix2Pix system, released last year, which can exhibit virtual worlds, sources added.

  • share
  • Twitter
  • Facebook
  • LinkedIn


About Author

Nikita Chaurasia    

Nikita Chaurasia

Having always been daft at wordplay, Nikita Chaurasia, post the completion of post-graduation, commenced her journey into the content generation cosmos. Endowed with a professional MBA degree in Advertising and Public Relations, Nikita strives to integrate her creativ...

Read More

More News By Nikita Chaurasia

Google sued by Justice Department for illicitly holding monopoly power
Google sued by Justice Department for illicitly holding monopoly power
By Nikita Chaurasia

The U.S. Justice Department has reportedly filed a landmark lawsuit against Google LLC of illegally safeguarding its monopoly in order to dominate the search and advertising vertical. If reports are to be believed, the recent antitrust case against G...

Flybe’s flight services to be revived by Thyme Opco post acquisition
Flybe’s flight services to be revived by Thyme Opco post acquisition
By Nikita Chaurasia

COVID-19 restrictions pushed Flybe into administration in March 2020, putting over 2,400 jobs at risk. The acquisition will allow Flybe to restart its operations as a regional airliner in the U.K. It has been speculated that U.K.-based airline c...

Britain hits an absurdly high average asking price for homes
Britain hits an absurdly high average asking price for homes
By Nikita Chaurasia

Reportedly, the average asking price of houses in Britain has reached an all-time high, with buyers willing to spend more for larger properties after experiencing the COVID-19 lockdown. Sources with relevant information stated that for the first tim...