Scipediacontent: Scipediacontent moved page Draft Content 433563106 to Schneider et al 2018a

2021-02-02T01:34:41Z

Scipediacontent moved page Draft Content 433563106 to Schneider et al 2018a

Scipediacontent: Created page with " == Abstract == In this paper, we show how absolute orientation measurements provided by low-cost but high-fidelity IMU sensors can be integrated into the KinectFusion pipeli..."

2021-02-02T01:34:35Z

Created page with " == Abstract == In this paper, we show how absolute orientation measurements provided by low-cost but high-fidelity IMU sensors can be integrated into the KinectFusion pipeli..."

New page

== Abstract ==

In this paper, we show how absolute orientation measurements provided by low-cost but high-fidelity IMU sensors can be integrated into the KinectFusion pipeline. We show that integration improves both runtime, robustness and quality of the 3D reconstruction. In particular, we use this orientation data to seed and regularize the ICP registration technique. We also present a technique to filter the pairs of 3D matched points based on the distribution of their distances. This filter is implemented efficiently on the GPU. Estimating the distribution of the distances helps control the number of iterations necessary for the convergence of the ICP algorithm. Finally, we show experimental results that highlight improvements in robustness, a speed-up of almost 12%, and a gain in tracking quality of 53% for the ATE metric on the Freiburg benchmark.

Comment: CVPR Workshop on Visual Odometry and Computer Vision Applications Based on Location Clues 2018

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1802.03980 http://arxiv.org/abs/1802.03980]

* [http://arxiv.org/pdf/1802.03980 http://arxiv.org/pdf/1802.03980]

* [http://xplorestaging.ieee.org/ielx7/8575058/8575239/08575358.pdf?arnumber=8575358 http://xplorestaging.ieee.org/ielx7/8575058/8575239/08575358.pdf?arnumber=8575358],
: [http://dx.doi.org/10.1109/cvprw.2018.00198 http://dx.doi.org/10.1109/cvprw.2018.00198]

* [https://dblp.uni-trier.de/db/journals/corr/corr1802.html#abs-1802-03980 https://dblp.uni-trier.de/db/journals/corr/corr1802.html#abs-1802-03980],
: [http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w30/Giancola_Integration_of_Absolute_CVPR_2018_paper.pdf http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w30/Giancola_Integration_of_Absolute_CVPR_2018_paper.pdf],
: [https://arxiv.org/abs/1802.03980 https://arxiv.org/abs/1802.03980],
: [https://arxiv.org/pdf/1802.03980.pdf https://arxiv.org/pdf/1802.03980.pdf],
: [https://ui.adsabs.harvard.edu/abs/2018arXiv180203980G/abstract https://ui.adsabs.harvard.edu/abs/2018arXiv180203980G/abstract],
: [https://ieeexplore.ieee.org/document/8575358 https://ieeexplore.ieee.org/document/8575358],
: [http://export.arxiv.org/pdf/1802.03980 http://export.arxiv.org/pdf/1802.03980],
: [https://repository.kaust.edu.sa/handle/10754/627172 https://repository.kaust.edu.sa/handle/10754/627172],
: [http://openaccess.thecvf.com/content_cvpr_2018_workshops/w30/html/Giancola_Integration_of_Absolute_CVPR_2018_paper.html http://openaccess.thecvf.com/content_cvpr_2018_workshops/w30/html/Giancola_Integration_of_Absolute_CVPR_2018_paper.html],
: [https://fr.arxiv.org/pdf/1802.03980 https://fr.arxiv.org/pdf/1802.03980],
: [https://za.arxiv.org/abs/1802.03980 https://za.arxiv.org/abs/1802.03980],
: [https://au.arxiv.org/pdf/1802.03980 https://au.arxiv.org/pdf/1802.03980],
: [https://it.arxiv.org/pdf/1802.03980 https://it.arxiv.org/pdf/1802.03980],
: [https://jp.arxiv.org/abs/1802.03980 https://jp.arxiv.org/abs/1802.03980],
: [https://export.arxiv.org/abs/1802.03980 https://export.arxiv.org/abs/1802.03980],
: [https://academic.microsoft.com/#/detail/2786157287 https://academic.microsoft.com/#/detail/2786157287]

← Older revision	Revision as of 01:34, 2 February 2021
(No difference)

Schneider et al 2018a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 433563106 to Schneider et al 2018a

Scipediacontent: Created page with " == Abstract == In this paper, we show how absolute orientation measurements provided by low-cost but high-fidelity IMU sensors can be integrated into the KinectFusion pipeli..."