Fyusion, a computer vision/machine learning company, is demonstrating a new 3D imaging technology this week at SIGGRAPH 2019. The technology, aimed at providing digital marketers with photoreal images of products and scenes, uses light field technology to attain greater realism. The company has raised $70 million, including $3 million from Japan’s Itochu trading company and a “strategic investment” from Cox Automotive. The software is already being used for commercial purposes in automotive, retail and fashion industries.

VentureBeat reports that the San Francisco-based company’s earlier focus on converting smartphone pictures into 3D holographic images helped it “gain more than 150 million monthly active users.” This more recent business, however, is likely be more lucrative. Cox Automotive, a digital wholesale market for used vehicles, is using Fyusion software to “display 3D images of cars on its websites,” and Itochu is using it “to show images of models wearing outfits on its brands’ retail sites.”

Among its strengths, Fyusion’s technology can handle “fine-grained textures like grass and foliage, transparent surfaces, and reflections” — features already available to professionals but not to “the masses.”

“Fyusion’s technology is groundbreaking because it is low cost and produces the highest quality results,” said a company statement. “It’s also conceptually simple.” The technology relies on a deep network “to promote each source view to a layered representation of the scene, advancing recent work on the multiplane image (MPI) representation … [and] then synthesizes novel views by blending renderings from adjacent layered representations.”

The result, according to Fyusion, “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 chief executive Radu Rusu. Fyusion technology can be found on GitHub, where it “is available for testing.”