Sparse depth estimation using multi-view 3D modeling

Jinjin Li, Lina Karam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a 2D to 3D conversion system from multiple views based on the computation of a sparse depth map. This method is able to deal with the multiple views obtained from uncalibrated hand-held cameras without prior knowledge of the camera parameters or scene geometry. The obtained reconstructed sparse depth maps of feature points in 3D scenes provide accurate relative depth information of the objects. Sample ground-truth depth data points are used to calculate a scale factor in order to estimate the true depth by scaling the obtained relative depth using the estimated scale factor. Results are presented to illustrate the performance of the developed system. It is shown that the implemented 2D to 3D conversion system results in a reconstructed depth map that matches the ground-truth depth data.

Original languageEnglish (US)
Title of host publication2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings
Pages151-154
Number of pages4
DOIs
StatePublished - 2012
Event2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Las Vegas, NV, United States
Duration: Jan 12 2011Jan 14 2011

Other

Other2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012
CountryUnited States
CityLas Vegas, NV
Period1/12/111/14/11

Fingerprint

Cameras
Geometry

Keywords

  • 3D reconstruction
  • Depth estimation
  • Euclidean reconstruction
  • Multi-view
  • Sparse depth map

ASJC Scopus subject areas

  • Signal Processing

Cite this

Li, J., & Karam, L. (2012). Sparse depth estimation using multi-view 3D modeling. In 2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings (pp. 151-154). [6152468] https://doi.org/10.1109/ESPA.2012.6152468

Sparse depth estimation using multi-view 3D modeling. / Li, Jinjin; Karam, Lina.

2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings. 2012. p. 151-154 6152468.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, J & Karam, L 2012, Sparse depth estimation using multi-view 3D modeling. in 2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings., 6152468, pp. 151-154, 2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012, Las Vegas, NV, United States, 1/12/11. https://doi.org/10.1109/ESPA.2012.6152468
Li J, Karam L. Sparse depth estimation using multi-view 3D modeling. In 2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings. 2012. p. 151-154. 6152468 https://doi.org/10.1109/ESPA.2012.6152468
Li, Jinjin ; Karam, Lina. / Sparse depth estimation using multi-view 3D modeling. 2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings. 2012. pp. 151-154
@inproceedings{5d4511c1c69a4430af00cc591427b7d0,
title = "Sparse depth estimation using multi-view 3D modeling",
abstract = "This paper presents a 2D to 3D conversion system from multiple views based on the computation of a sparse depth map. This method is able to deal with the multiple views obtained from uncalibrated hand-held cameras without prior knowledge of the camera parameters or scene geometry. The obtained reconstructed sparse depth maps of feature points in 3D scenes provide accurate relative depth information of the objects. Sample ground-truth depth data points are used to calculate a scale factor in order to estimate the true depth by scaling the obtained relative depth using the estimated scale factor. Results are presented to illustrate the performance of the developed system. It is shown that the implemented 2D to 3D conversion system results in a reconstructed depth map that matches the ground-truth depth data.",
keywords = "3D reconstruction, Depth estimation, Euclidean reconstruction, Multi-view, Sparse depth map",
author = "Jinjin Li and Lina Karam",
year = "2012",
doi = "10.1109/ESPA.2012.6152468",
language = "English (US)",
isbn = "9781467308984",
pages = "151--154",
booktitle = "2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings",

}

TY - GEN

T1 - Sparse depth estimation using multi-view 3D modeling

AU - Li, Jinjin

AU - Karam, Lina

PY - 2012

Y1 - 2012

N2 - This paper presents a 2D to 3D conversion system from multiple views based on the computation of a sparse depth map. This method is able to deal with the multiple views obtained from uncalibrated hand-held cameras without prior knowledge of the camera parameters or scene geometry. The obtained reconstructed sparse depth maps of feature points in 3D scenes provide accurate relative depth information of the objects. Sample ground-truth depth data points are used to calculate a scale factor in order to estimate the true depth by scaling the obtained relative depth using the estimated scale factor. Results are presented to illustrate the performance of the developed system. It is shown that the implemented 2D to 3D conversion system results in a reconstructed depth map that matches the ground-truth depth data.

AB - This paper presents a 2D to 3D conversion system from multiple views based on the computation of a sparse depth map. This method is able to deal with the multiple views obtained from uncalibrated hand-held cameras without prior knowledge of the camera parameters or scene geometry. The obtained reconstructed sparse depth maps of feature points in 3D scenes provide accurate relative depth information of the objects. Sample ground-truth depth data points are used to calculate a scale factor in order to estimate the true depth by scaling the obtained relative depth using the estimated scale factor. Results are presented to illustrate the performance of the developed system. It is shown that the implemented 2D to 3D conversion system results in a reconstructed depth map that matches the ground-truth depth data.

KW - 3D reconstruction

KW - Depth estimation

KW - Euclidean reconstruction

KW - Multi-view

KW - Sparse depth map

UR - http://www.scopus.com/inward/record.url?scp=84863254548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863254548&partnerID=8YFLogxK

U2 - 10.1109/ESPA.2012.6152468

DO - 10.1109/ESPA.2012.6152468

M3 - Conference contribution

SN - 9781467308984

SP - 151

EP - 154

BT - 2012 IEEE International Conference on Emerging Signal Processing Applications, ESPA 2012 - Proceedings

ER -