EUROGRAPHICS 2014 / E. Galin and M. Wand Short Paper Combining Inertial Navigation and ICP for Real-time 3D Surface

We present a novel method to improve the robustness of real-time 3D surface reconstruction by incorporating inertial sensor data when determining inter-frame alignment. With commodity inertial sensors, we can signifi-cantly reduce the number of iterative closest point (ICP) iterations required per frame. Our system is also able to determine when ICP tracking becomes unreliable and use inertial navigation to correctly recover tracking, even after significant time has elapsed. This enables less experienced users to more quickly acquire 3D scans. We apply our framework to several different surface reconstruction tasks and demonstrate that enabling inertial navigation allows us to reconstruct scenes more quickly and recover from situations where reconstructing without IMU data produces very poor results. 1 Introduction and Related Work With the advent of commodity real-time RGB-D sensors such as the Microsoft Kinect and the Asus Xtion, 3D re-construction has gained new momentum in the computer graphics and vision community. In particular, online recon