Lights, Camera, Artificial Action: Start-Up Is Taking A.I. to the Movies<br />They were shooting a powder-blue 1962 Austin Mini, but through special effects the rusted relic would be transformed into an autonomous vehicle<br />that looked more like the DeLorean from “Back to the Future.”<br />Stepping back from the camera, Mr. Avalos referred wryly to the movie he was filming as “Project Unemployment.” The film was a way of testing<br />new technology from a start-up called Arraiy, which is trying to automate the creation of digital effects for movies, television and games.<br />Thanks to improvements in so-called neural networks — complex algorithms<br />that can learn tasks by analyzing vast amounts of data — these systems can edit noise and mistakes out of images or apply simple effects and create highly realistic images of very fake people or help graft one person’s head onto the body of someone else.<br />Inside Arraiy’s offices — the old auto body shop — Mr. Bradski and Mr. Rublee are building computer algorithms<br />that can learn design tasks by analyzing years of work by movie effects houses.<br />For every second of movie time, armies of designers can spend hours isolating people<br />and objects in raw camera footage, digitally building new images from scratch, and combining the two as seamlessly as possible.<br />By CADE METZMARCH 26, 2018<br />PALO ALTO, Calif. — Inside an old auto body shop here in Silicon Valley, Stefan Avalos pushed a movie camera down a dolly track.<br />Backed by more than $10 million in financing from the Silicon Valley venture firm Lux Capital, SoftBank Ventures<br />and others, Arraiy is part of a widespread effort spanning industry and academia and geared toward building systems that can generate and manipulate images on their own.
