Instant Motion Tracking

Instant Motion Tracking and Its Applications to Augmented Reality

Jianing Wei, Genzhi Ye, Tyler Mullen, Matthias Grundmann, Adel Ahmadyan, Tingbo Hou

Abstract

Augmented Reality (AR) brings immersive experiences to users. With recent advances in computer vision and mobile computing, AR has scaled across platforms, and has increased adoption in major products. One of the key challenges in enabling AR features is proper anchoring of the virtual content to the real world, a process referred to as tracking. In this paper, we present a system for motion tracking, which is capable of robustly tracking planar targets and performing relative-scale 6DoF tracking without calibration. Our system runs in real-time on mobile phones and has been deployed in multiple major products on hundreds of millions of devices.

Overview

Our instant motion tracking system offers the following contributions:

  • Instant initialization of AR session and 6DoF poses
  • Robust against degenerate cases such as planar scenes, no motion, and pure rotation
  • Calibration-free real-time system, runs on any mobile device

Our system consists of:

  • A motion analysis module
  • A region tracking module, and either a
  • Planar target tracking module for planar surfaces or
  • Pose estimation module for calibration-free 6DoF tracking with relative scale


Paper

Presenting at CVPR 2019 Third Workshop on Computer Vision for AR/VR

June 17, 2019, Long Beach, CA

[PDF]

Google Research Blog

The Instant Motion Tracking Behind Motion Stills AR

Published February 6, 2018