Skip to main content

3D News

In our opinion, there are far too few people out there taking 3D images and one major reason is the perceived difficulty barrier—taking two images and combining them for a stereo effect with special software or using custom twin digital SLR camera rigs is simply too complex and/or expensive for most of us mere mortals. Enter the 3D-capable point-and-shoot, the latest of which is Panasonic’s upcoming Lumix DMC-3D1. Similar to Fujifilm...

Recent Blog Entries

In the real world, our hands are our guides. We feel with them, we manipulate with them, we explore with them. We use them to eat, dress and primp ourselves, make a living, and connect with others.

And yet, in the virtual world, we’re lucky if we can use them at all.

A team of researchers at Purdue University hopes to change that with DeepHand, a deep learning-powered system for interpreting hand movements in virtual environments.

By combining depth-sensing cameras and a convolutional neural network trained on GPUs to interpret 2.5 million hand poses and configurations, the team has taken us a large step closer to being able to use our dexterity while interacting with 3D virtual objects.

Natural Interface

DeepHand fulfills the long-time vision of its lead researcher, Karthik Ramani, the Donald W. Feddersen Professor of Mechanical Engineering, at Purdue.

“I’ve always wanted to design and develop our hands as a key part of a user interface element, because we do so much in the real world with our hands so naturally,” Ramani said. “The use of hand gestures offers smart and intuitive communication with 3D objects.”

Ramani said that the emergence of more affordable depth-sensing cameras has broadened the possibilities for hand-movement recognition, and has raised expectations for more natural use of hands in human-computer interfaces.

GPUs are helping the cause by speeding up the training of convolutional neural networks such as the one created for DeepHand. Ramani and his two graduate student researchers, Ayan Sinha and Chiho Choi, used NVIDIA GPUs to train their network, and Ramani said they were able to complete the process 2-3 times faster than if they’d used CPUs.

Working Out the Kinks

Despite the team’s clear progress, numerous challenges remain. Parts of the fingers and hands often block the view of the camera, making interpretation of hand motions sometimes impossible. The hand’s numerous joints and sheer volume of potential motions are almost limitless. What’s more, parts of the hand look so similar to one another that the system can sometimes struggle to identify what part it’s looking at.

“Figuring out the exact hand location and angles of all the joints through vision is not as easy as fitting a line through a bunch of points,” Ramani said. “It is a much harder problem.”

Fortunately for Ramani, the project has support in the form of National Science Foundation funding routed through his affiliated startup company, ZeroUI, which is focused on the development of the hands as a user interface. (The company has gained some attention for its Ziro modular construction kit for building hand-controlled robotic toys.)

Big Plans

Ramani’s team plans to eventually commercialize DeepHand through ZeroUI. But he says they have more work to do in reducing the “noise” that interferes with hand motion interpretations before it starts developing augmented and virtual reality applications.

“The hand model has to be made robust and utilitarian for real-world AR and VR use,” he said. He and his team plan to keep pushing toward just that.

The team presented its research paper at the 2016 IEEE Conference on Computer Vision and Pattern Recognition held in Las Vegas earlier this summer.

The post Freeing Our Fingers: Handing Over VR’s Toughest Challenge to GPUs appeared first on The Official NVIDIA Blog.

Artificial intelligence and deep learning. VR and augmented reality. Autonomous vehicles and intelligent machines.

At the center of these technologies is GPU computing. And the GPU Technology Conference is where the people behind these technologies and dozens more connect to shape the future.

Share your innovation: Become a featured GTC speaker.

GTC 2017 provides developers and thought leaders with the opportunity to share their work with thousands of the world’s brightest minds. Past speakers have included developers from Audi, ESPN, Facebook, Google, IBM, Toyota and many more companies, along with top researchers from universities worldwide.

Enter your submission now for talks, research posters and instructor-led labs at the May 8-11 event, in Silicon Valley.

Startups are also invited to apply to join the daylong Emerging Companies Summit. One highlight: the Early Stage Challenge, where CEOs get four minutes to pitch their company’s GPU innovation to a panel of expert judges for a shot at a $100,000 cash prize, awarded on the spot.

Showcase for GPU Developers

GTC is the world’s most important GPU developer conference. The 2016 event had more than 5,500 attendees, and 600+ sessions on GPU breakthroughs in science, technology and industry.

Accepted submissions showing how GPUs are transforming accelerated computing and graphics will earn an All-Access conference pass. Plus you’ll get the opportunity to connect with experts from NVIDIA, a who’s who of top business and academic organizations, and 250+ global press and analysts.

Lead hands-on learning at one of GTC’s many labs.

Attendees can also participate in developer labs and social events and gain hands-on training on the innovative ways that GPU technologies are changing the world.

Call for Submissions

Submit your ideas for GTC 2017.

To get in on the action, submit your creative and groundbreaking work using GPUs:

See highlights from GTC 2016 here.

The post GTC 2017: Call for Submissions Now Open for World’s Top GPU Developer Event appeared first on The Official NVIDIA Blog.