10999

Real-time High Resolution Fusion of Depth Maps on GPU

Dmitry Trifonov
Artec Group Inc./Keldysh Institute of Applied Mathematics RAS
arXiv:1311.7194 [cs.GR], (28 Nov 2013)

@article{2013arXiv1311.7194T,

   author={Trifonov}, D.},

   title={"{Real-time High Resolution Fusion of Depth Maps on GPU}"},

   journal={ArXiv e-prints},

   archivePrefix={"arXiv"},

   eprint={1311.7194},

   primaryClass={"cs.GR"},

   keywords={Computer Science – Graphics, Computer Science – Computer Vision and Pattern Recognition},

   year={2013},

   month={nov},

   adsurl={http://adsabs.harvard.edu/abs/2013arXiv1311.7194T},

   adsnote={Provided by the SAO/NASA Astrophysics Data System}

}

Download Download (PDF)   View View   Source Source   

2013

views

A system for live high quality surface reconstruction using a single moving depth camera on a commodity hardware is presented. High accuracy and real-time frame rate is achieved by utilizing graphics hardware computing capabilities via OpenCL and by using sparse data structure for volumetric surface representation. Depth sensor pose is estimated by combining serial texture registration algorithm with iterative closest points algorithm (ICP) aligning obtained depth map to the estimated scene model. Aligned surface is then fused into the scene. Kalman filter is used to improve fusion quality. Truncated signed distance function (TSDF) stored as block-based sparse buffer is used to represent surface. Use of sparse data structure greatly increases accuracy of scanned surfaces and maximum scanning area. Traditional GPU implementation of volumetric rendering and fusion algorithms were modified to exploit sparsity to achieve desired performance. Incorporation of texture registration for sensor pose estimation and Kalman filter for measurement integration improved accuracy and robustness of scanning process.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: