Google’s latest Project Starline prototype uses AI to create 3D images of people

Image credit: Google

At I/O today, Google unveiled the latest prototype of Project Starline, a 3D teleconferencing video booth. At first glance, the biggest difference is the significantly reduced hardware. An early model, unveiled late last year, used multiple cameras to capture the speaker from all angles. This time, however, the system has only “a few” on board, relying on AI and ML to generate a convincing 3D image of him of the subject.

According to Google, these hardware updates have allowed the system to go “from the size of a restaurant booth to a flat-screen TV.” In a blog post it said:

Our early Project Starline prototypes took up an entire room and required complex hardware such as infrared emitters and special cameras to create a live 3D model of the person you were talking to. While the results were impressive, the size and complexity of the system made it difficult to deploy in many offices today.

Google has already started testing the latest prototype with a number of prominent partners, including T-Mobile, Salesforce and WeWork.

“Trust and innovation are core values ​​at Salesforce,” said Salesforce SVP Andy White. “Project Starline has the potential to help create authentic, immersive connections that foster deeper relationships with both employees and customers, increase trust and transparency, and improve productivity and efficiency. I have.”

The news arrived following Logitech’s Project Ghost conference call booth. However, this device offers a more two-dimensional experience in a larger form factor. Both products have emerged in a workforce transformation where working from home has become the rule, not the exception, for many companies.

No details were given about the schedule or pricing of the new system.