At the Web Summit technology conference on Tuesday, Mike Schroepfer, chief technology officer at Facebook, Inc. (NASDAQ:FB) introduced a revolutionary breakthrough in technology called Caffe2Go. The style transfer feature allows you to edit videos to look like Van Gogh paintings. Normally, this would be difficult because the video has to be sent to data centers to be processed with a fast internet connection.
To combat this, Facebook has produced an AI into its app that allows people to add filters to their videos in real-time, cutting down computing tasks fast enough to be done on mobile devices. “This is one application of AI on the device, it’s one of the first. But the real breakthrough here is being able to train and build models on a big server…and deploy them directly to your pocket so you can run them in real time wherever you are. That is the exciting future of AI,” Schroepfer reported during a speech.
“By condensing the size of the AI model used to process images and videos by 100x, we’re able to run various deep neural networks with high efficiency on both iOS and Android,” Facebook wrote in a blog post.
The AI can mimic “neural networks” within the human brain to learn and make connections. This key technology can also link towards virtual reality. “In VR image and video processing software powered by computer vision is improving immersive experiences and helping to support hardware advances. Earlier this year we announced a new stabilization technology for 360 videos, powered by computer vision. And computer vision software is enabling inside-out tracking to help usher in a whole new category of VR beyond PC and mobile, as we announced at Oculus Connect 3 last month. This will help make it possible to build high-quality, standalone VR headsets that aren’t tethered to a PC,” Schroepfer wrote in a blog post.
Facebook is attempting to make computers “learn, plan and reason like humans.”