Magic Leap Researchers Reveal “Deep SLAM” Tracking Algorithm
Authored by Magic Leap researchers Daniel DeTone, Tomasz Malisiewicz, and Andrew Rabinovich, the paper describes a tracking system powered by two deep convolutional neural networks (CNNs)—a type of artificial ‘brain’ used for image processing. Called MagicPoint and MagicWarp, the researchers contend the two CNNs allow for a system that’s “fast and lean, easily running 30+ FPS on a single CPU.”
Here’s the quick and dirty: According to the paper, MagicPoint operates on single images and creates 2D points important to the purpose of tracking, with these points destined to be fed into a simultaneous localization and mapping (SLAM) visual algorithm. Comparing their network to classical point detectors, the team discovered “a significant performance gap in the presence of image noise.”
Because calculating the shape of objects as they move around isn’t an easy task—it could be either the object or the viewer moving—MagicWarp’s job is to use a pair of these images containing the 2D points generated by MagicPoint to essentially predict motion as it models the world around it.