NVIDIA Canvas Uses AI to Turn Your Doodles into ‘Photos’

NVIDIA has announced Canvas, an app that is available as a free beta that it says brings real-time painting tools to anyone with an NVIDIA RTX GPU. It uses artificial intelligence to make rudimentary sketches or doodles into photorealistic scenes. Canvas is part of NVIDIA Studio, which is a program that provides artists and creators […]

NVIDIA Canvas Uses AI to Turn Your Doodles into ‘Photos’

NVIDIA has announced Canvas, an app that is available as a free beta that it says brings real-time painting tools to anyone with an NVIDIA RTX GPU. It uses artificial intelligence to make rudimentary sketches or doodles into photorealistic scenes.

Canvas is part of NVIDIA Studio, which is a program that provides artists and creators with both hardware and software tools to assist in bringing creative visions to life. Canvas appears to be the consumer-facing version of the app that NVIDIA showcased in 2019, but what is shown here is far more advanced than what was teased back then.

In Canvas, users can start sketching simple shapes and lines using a palette of 15 tools such as mountains, clouds, grass, or weather effects and the artificial intelligence model will turn those into a photorealistic scene in real-time.

What looks like a sketch made in Microsoft Paint is transformed into a lifelike scene instantly and with jaw-dropping quality.

“The tool allows artists to use style filters, changing a generated image to adopt the style of a particular painter,” NVIDIA explains. “NVIDIA Canvas isn’t just stitching together pieces of other images, or cutting and pasting textures, but creating brand new images, just like an artist would.”

The algorithm is aided by the tools palette in Canvas so that it understands what the artist is intending to show, but the results are still extremely impressive. NVIDIA says that the creative applications of the tool are “endless” and that it can help artists ideate faster than before, which is normally a far more time-consuming task.

Lines and shapes turn into life-like landscapes in seconds. | NVIDIA

“It can also bring time savings to a range of creators and designers,” NVIDIA explains. “Consider an art director on a time crunch who needs to refine the hero product in an ad campaign. A landscape will complete the shot. Using NVIDIA Canvas, the director is only a few clicks from generating several beautifully rendered images. In a matter of moments, the tool provides multiple options for the client to review, saving precious time before finalizing the featured product.”

Canvas uses a form of artificial intelligence called “generative adversarial networks,” or GAN. It is the same technology that NVIDIA has used in previous AI algorithms, like its tool that can create photorealistic faces. GANs consist of a generator and a discriminator that work together. A generator aims to convert material maps into images, and the discriminator understands certain aspects of what is generated. For example, the discriminator knows that water has reflections, and can tell the generator to create a representation of that.

“To deliver realistic portraits for artists, the GAN has been trained on an NVIDIA DGX system using over 5 million images,” NVIDIA says.

The Canvas beta can be downloaded for free now, and NVIDIA is soliciting feedback on its forums.

Source : Peta Pixel More   

What's Your Reaction?

like
0
dislike
0
love
0
funny
0
angry
0
sad
0
wow
0

Next Article

Instagram Tests ‘Suggested Posts’ That Can Appear Ahead of Friends

Instagram is reportedly testing a feature with a “small number” of users where its “suggested posts” feature will expand beyond just when you’ve reached the end of your feed and will be mixed throughout a browsing experience, possibly coming ahead of posts from those users follow. In a confirmation to The Verge, Instagram says that […]

Instagram Tests ‘Suggested Posts’ That Can Appear Ahead of Friends

Instagram is reportedly testing a feature with a “small number” of users where its “suggested posts” feature will expand beyond just when you’ve reached the end of your feed and will be mixed throughout a browsing experience, possibly coming ahead of posts from those users follow.

In a confirmation to , Instagram says that reception to the “suggested posts” feature was so positive that the company decided to try and mix those suggestions in with the average viewing experience, sometimes ahead of photos and videos from people a user explicitly follows.

Additionally, Instagram is testing new controls that will allow users to add a specific topic of interest for suggested posts as well as the ability to “snooze” the recommendations for 30 days or hide them from a feed entirely. “Suggested posts” is a feature that Instagram added last year, but prior to this small test was only ever seen after a user saw everything from all people they followed that was shared.

This shift would make Instagram theoretically function similarly to how YouTube manages its “home” page, which highlights content that is a mix of videos made by those a user is subscribed to as well as videos that YouTube’s algorithm thinks are of interest. YouTube leans so heavily on this analytics-forward approach that subscriptions have fallen in importance over the years.

If Instagram were to adopt placing suggested posts for all users, it may have a dramatic impact on how the social network functions. Instagram has a vested interest in keeping users on the platform for as long as possible, and keep them coming back. As such, the social network should not necessarily need to put as much value on showing a user content from people they follow as opposed to delivering photos and videos that keep them engaged. As YouTube has shown, just because a person subscribes to a Channel doesn’t mean that the user necessarily wants to see all content that Channel produces.

That’s the theory, anyway, and it might have ramifications in the long term for content creators who rely on Instagram to reach an audience, especially if suggested posts become more popular and show higher engagement than that of specifically followed accounts.

Algorithm-focused approaches have generally superseded ones that focus on giving users complete control over what they see. Facebook and Instagram both ditched a timeline-based approach years ago, and Twitter defaults users to the “Home” view instead of “Latest Tweets” which uses an algorithm to determine the most interesting content. At least in Twitter’s case, switching back to Latest Tweets is an option.

Instagram did not specify how many people its “suggested posts” test would affect nor how long it intended to test the feature.

Source : Peta Pixel More   

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies.