Why Magic Leap’s Deep SLAM Tracking Algorithm Is A Major Leap Forward

Greenlight InsightsAnalysis, Augmented Reality

Magic Leap Machine Learning

Last week, Magic Leap, the Google and Alibaba-funded startup valued at $4.5 billion, released a research paper demonstrating a major breakthrough in computer vision and its SLAM tracking algorithm. The Plantation, FL-based company's technology superimposes 3D computer-generated imagery over real world objects by projecting a digital light field directly into the eye. Magic Leap is widely considered one of the most important, yet highly-secretive, companies in the augmented reality technology ecosystem.

Senior Technology Analyst, Greg Sanders, one of the co-authors of the 2017 Augmented Reality Industry Report explained the importance of Magic Leap's breakthrough:

"Magic Leap has developed a novel machine vision technique for the standalone AR headset they are developing. The new technique is based on two deep convolutional neural networks (CNNs) called MagicPoint and MagicWarp. MagicPoint processes 2D images to identify corners, and assigns points to each identified corner. Then MagicWarp compares the before and after point locations to determine and predict movement. Each convolutional neuron processes data only for its receptive field, allowing CNNs to interpret movement in the images. The result, according to Magic Leap is a system that's “fast and lean, easily running 30+ FPS on a single CPU. The Magic Leap vision tech may help minimize the number of sensors needed in their headset, especially compared to an estimated 11 or more sensors in the Microsoft Hololens."

To learn more about Magic Leap, the marketplace development, and the future outlook for the augmented reality technology sector, pre-order the 2017 Augmented Reality Industry Report.

Share this Post