Statistical Optimization for 3-D Reconstruction from a Single View

Kenichi KANATANI; Yasuyuki SUGAYA

doi:10.1093/ietisy/e88-d.10.2260

Statistical Optimization for 3-D Reconstruction from a Single View

Kenichi KANATANI, Yasuyuki SUGAYA

Full Text Views

0

Share
Cite this

Summary :

We analyze the noise sensitivity of the focal length computation, the principal point estimation, and the orthogonality enforcement for single-view 3-D reconstruction based on vanishing points and orthogonality. We point out that due to the nonlinearity of the problem the standard statistical optimization is not very effective. We present a practical compromise for avoiding the computational failure and preserving high accuracy, allowing a consistent 3-D shape in the presence of however large noise.

Publication: IEICE TRANSACTIONS on Information Vol.E88-D No.10 pp.2260-2268

Publication Date: 2005/10/01

Publicized

Online ISSN

DOI: 10.1093/ietisy/e88-d.10.2260

Type of Manuscript: Special Section PAPER (Special Section on Image Recognition and Understanding)

Category

Cite this

Copy

Kenichi KANATANI, Yasuyuki SUGAYA, "Statistical Optimization for 3-D Reconstruction from a Single View" in IEICE TRANSACTIONS on Information, vol. E88-D, no. 10, pp. 2260-2268, October 2005, doi: 10.1093/ietisy/e88-d.10.2260.
Abstract: We analyze the noise sensitivity of the focal length computation, the principal point estimation, and the orthogonality enforcement for single-view 3-D reconstruction based on vanishing points and orthogonality. We point out that due to the nonlinearity of the problem the standard statistical optimization is not very effective. We present a practical compromise for avoiding the computational failure and preserving high accuracy, allowing a consistent 3-D shape in the presence of however large noise.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.10.2260/_p

Copy

@ARTICLE{e88-d_10_2260,
author={Kenichi KANATANI, Yasuyuki SUGAYA, },
journal={IEICE TRANSACTIONS on Information},
title={Statistical Optimization for 3-D Reconstruction from a Single View},
year={2005},
volume={E88-D},
number={10},
pages={2260-2268},
abstract={We analyze the noise sensitivity of the focal length computation, the principal point estimation, and the orthogonality enforcement for single-view 3-D reconstruction based on vanishing points and orthogonality. We point out that due to the nonlinearity of the problem the standard statistical optimization is not very effective. We present a practical compromise for avoiding the computational failure and preserving high accuracy, allowing a consistent 3-D shape in the presence of however large noise.},
keywords={},
doi={10.1093/ietisy/e88-d.10.2260},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - Statistical Optimization for 3-D Reconstruction from a Single View
T2 - IEICE TRANSACTIONS on Information
SP - 2260
EP - 2268
AU - Kenichi KANATANI
AU - Yasuyuki SUGAYA
PY - 2005
DO - 10.1093/ietisy/e88-d.10.2260
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2005
AB - We analyze the noise sensitivity of the focal length computation, the principal point estimation, and the orthogonality enforcement for single-view 3-D reconstruction based on vanishing points and orthogonality. We point out that due to the nonlinearity of the problem the standard statistical optimization is not very effective. We present a practical compromise for avoiding the computational failure and preserving high accuracy, allowing a consistent 3-D shape in the presence of however large noise.
ER -