Robotics: Science and Systems XIV

FlashFusion: Real-time Globally Consistent Dense 3D Reconstruction using CPU Computing

Lei Han, Lu Fang

Abstract:

Aiming at the practical usage of dense 3D reconstruction on portable devices, we propose FlashFusion, a Fast LArge-Scale High-resolution (sub-centimeter level) 3D reconstruction system without the use of GPU computing. It enables globally-consistent localization through a robust yet fast global bundle adjustment scheme, and realizes spatial hashing based volumetric fusion running at 300Hz and rendering at 25Hz via highly efficient valid chunk selection and mesh extraction schemes. Extensive experiments on both real world and synthetic datasets demonstrate that FlashFusion succeeds to enable real-time, globally consistent, high-resolution (5mm), and large-scale dense 3D reconstruction using highly-constrained computation, i.e., the CPU computing on portable devices.

Download:

Bibtex:

  
@INPROCEEDINGS{Han-RSS-18, 
    AUTHOR    = {Lei Han AND Lu Fang}, 
    TITLE     = {FlashFusion: Real-time Globally Consistent Dense 3D Reconstruction using CPU Computing}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2018}, 
    ADDRESS   = {Pittsburgh, Pennsylvania}, 
    MONTH     = {June}, 
    DOI       = {10.15607/RSS.2018.XIV.006} 
}