Computer vision and machine learning company Fyusion has unveiled a new 3D imaging technology for digital marketers with the aim of giving them new ways to show off photorealistic views of complex real-world scenes and products.
The company plans to show its new 3D imaging software at next week’s ACM Siggraph conference in Los Angeles. The software makes strides in the area of light field technology, allowing users to render cool scenes with greater realism. It is already being used in a number of commercial applications in automotive, retail, and fashion.
Back in May, Fyusion raised $3 million in funding from Japan’s Itochu trading company for technology that combines 3D imaging, computer vision, and machine learning to drive ecommerce.
A couple of years ago, the company was focused on taking smartphone pictures and converting them into 3D holographic images. This earlier strategy helped Fyusion gain more than 150 million monthly active users, but it wasn’t as lucrative as the new business it has recently embarked on.
Retailers have been using 3D imaging as part of their digital sales and marketing programs. The goal is to provide consumers with a vivid and realistic view of a product so they feel like they’re experiencing it before buying.
Earlier this year, Fyusion received a strategic investment from Cox Automotive, a leading digital wholesale marketplace for used vehicles that is using Fyusion’s software to display 3D images of cars on its websites. And last month Itochu revealed it is using Fyusion to show images of models wearing outfits on its brands’ retail sites. Fyusion’s tech handles notoriously difficult scenarios, including fine-grained textures like grass and foliage, transparent surfaces, and reflections.
3D imaging isn’t new, but making the technology accessible to the masses has proven elusive. Traditional 3D imaging methods rely on costly laser-scanning hardware and manual studio touch-ups; others eschew 3D entirely in favor of simple photo stitching.
Fyusion’s technology is cheap and produces quality results while being simple, the company said. First, Fyusion uses a deep network to promote each source view to a layered representation of the scene, advancing recent work on the multiplane image (MPI) representation. Fyusion then synthesizes novel views by blending renderings from adjacent layered representations. The result is a 4,000 times decrease in the number of images needed to produce a 3D image, making it easy for anyone to create high-quality 3D images using only a smartphone.
“These new advancements are a big step for light field research and as they continue to get incorporated into our products will give us a big new competitive advantage,” said Fyusion CEO Radu Rusu in a statement. “Our goal in announcing the work is to show that we are continuing to be at the forefront of the technology and implicitly that our products will continue to be the leading products in the space.”
A preview of Fyusion’s technology has been posted on GitHub and is available for testing. Members of the Fyusion R&D team will give a presentation based on the technology on Monday, July 29 at 10:45 a.m. Pacific at Siggraph.
San Francisco-based Fyusion has raised $70 million to date and has more than 50 employees.
VentureBeatVentureBeat's mission is to be a digital town square for technical decision-makers to gain knowledge about transformative technology and transact. Our site delivers essential information on data technologies and strategies to guide you as you lead your organizations. We invite you to become a member of our community, to access:
- up-to-date information on the subjects of interest to you
- our newsletters
- gated thought-leader content and discounted access to our prized events, such as Transform
- networking features, and more