Forget painting-style transfers, this A.I. creates realistic portraits of fake people

After selling the first artificial intelligence generated artwork earlier this year, deep learning algorithms are now tackling portraits — of made-up people that don’t exist. In a research paper, Nvidia recently shared the results of a generative adversarial network (GAN) trained to generate images of people while unsupervised.

The concept is based in part on style transfer technology, which transfers the style of one image onto another in order to do anything from building a photo app like Prisma to creating realistic deep fakes. Nvidia researchers redesigned the GAN to use a style transfer, while adjusting that style on each layer of code. The change, the researchers say, allows the software to generate high-level attributes like subtle differences in poses as well as random variation in features.

The researchers mixed the adjusted algorithms with a wider training dataset, one of which is the faces on Flickr instead of a database of celebrity faces, and adjusted the way the generator embeds the code for more realistic results that aren’t simply re-creating an existing person in a new photo. The researchers also switched between two different randomized codes for more variation in features.

While the GAN can randomly create images of people, the researchers also managed to control the results by using a style transfer to mix qualities from two different portraits. A “style” image mixed with a “source” image uses features like skin, eye, and hair color from the style image and applies it to the source image, which keeps the original’s gender, age and pose. The lighting styles and background of the style image also transfer to the source image.

The results show dramatic improvement over similar Nvidia research from four years ago, where the resulting images were black and white images with few details. The program’s not perfect — the system, for example, created some portraits with two different colored eyes and in others didn’t maintain facial symmetry.

While the paper shows impressive progress, the researchers didn’t detail the real-world use of such algorithms. Like the technology used for deep fakes, the ability to create an image of a fake person — though not a process that’s easy to replicate — raises concerns about misuse of the technology.

Emerging Tech

A.I.-generated text is supercharging fake news. This is how we fight back

A new A.I. tool is reportedly able to spot passages of text written by algorithm. Here's why similar systems might prove essential in a world of fake news created by smart machines.
Computing

Nvidia’s A.I. Playground lets you edit photos, experience deep learning research

Nvidia is making it easier to access information on deep learning research. It has launched an online space with three demos for image editing, styling, as well as photorealistic image synthesis. 
Computing

Nvidia’s smart paintbrush tool turns simple doodles into works of art

Nvidia has announced a new deep-learning-enhanced drawing app that can turn your doodles and sketches into highly realistic images. With Nvidia's GauGAN, simple sketches can be automatically embellished with more vivid details.
Emerging Tech

Awesome Tech You Can’t Buy Yet: Write music with your voice, make homemade cheese

Check out our roundup of the best new crowdfunding projects and product announcements that hit the web this week. You may not be able to buy this stuff yet, but it sure is fun to gawk!
Social Media

Twitter takes a cue from Instagram and Snapchat with new quick-swipe camera

Twitter is giving the "what's happening" treatment to photos and video by allowing users to access the in-app camera fast enough to catch and share the moment. The new Twitter camera is now accessible with a swipe.
Photography

The Lensbaby Composer Pro II with Edge 35 mimics tilt-shift blur for less cash

Want to create a tilt-shift image on a budget? The new Lensbaby Composer II with Edge 35 mimics the look of a tilt-shift lens for under $500. The new Edge 35 optic is part of the Composer Pro II optics system.
Photography

Loupedeck Plus can now edit video, audio with Final Cut Pro

The list of Loupedeck Plus-compatible software is growing. The photo-editing console now works with Final Cut Pro and Adobe Audition for video and audio editing. The controls can be configured to be used on either platform.
Photography

Photography News: Taking a smartphone photo probably saved this guy’s life

A man was snapping a photo in Australia when the smartphone stopped an arrow shot at his face. In this week's photography news, see Canon's plans for a stabilized mirrorless, Hasselblad's newest accessories, Samyang's latest lens, and more.
Deals

The best budget-friendly GoPro alternatives that won’t leave you broke

Cold weather is here, and a good action camera is the perfect way to record all your adventures. You don't need to shell out the big bucks for a GoPro: Check out these great GoPro alternatives, including some 4K cameras, that won’t leave…
Photography

Paper designs digitize in real time using an Illustrator-connected paper tablet

Love graphic design, but prefer the feel of real paper? The new Moleskine Paper Tablet - Creative Cloud Connected syncs with Adobe Illustrator in real time, turning paper sketches into digital drawings.
Photography

Insta-checkout? New Instagram service lets you shop without leaving the platform

Shopping on Instagram no longer means leaving the platform to checkout in a web browser. Instagram checkout launched in beta today with a handful of retailers, allowing users to checkout without leaving the app.
Computing

Make the most of your toner with our five favorite color laser printers

Color laser printers have improved dramatically over the years, and today's models offer both blazing print speeds and great image quality. Here are our favorite color laser printers, from massive all-in-ones to smaller budget options.
Photography

Sony’s latest sensor is stacked, backlit, and equipped with a global shutter

Say this five times fast: Backlit, stacked, global shutter sensor. Sony managed to cram all three technologies into one sensor. The result is a high-speed sensor with a higher resolution without sacrificing low-light quality.
Mobile

You can now use the innovative Red Hydrogen One on Google Fi

The Red Hydrogen One was first announced in 2017 and has been delayed a few times since then. Now, the Red Hydrogen One is finally available, featuring a Qualcomm Snapdragon 835, 6GB of RAM, and 128GB of storage.