Dense 3D reconstruction from specularity consistency

Diego Nehab; Tim Weyrich; Szymon Rusinkiewicz

doi:10.1109/CVPR.2008.4587683

Dense 3D reconstruction from specularity consistency

Diego Nehab, Tim Weyrich, Szymon Rusinkiewicz

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

29 Scopus citations

Abstract

In this work, we consider the dense reconstruction of specular objects. We propose the use of a specularity constraint, based on surface normal/depth consistency, to define a matching cost function that can drive standard stereo reconstruction methods. We discuss the types of ambiguity that can arise, and suggest an aggregation method based on anisotropic diffusion that is particularly suitable for this matching cost function. We also present a controlled illumination setup that includes a pair of cameras and one LCD monitor, which is used as a calibrated, variable-position light source. We use this setup to evaluate the proposed method on real data, and demonstrate its capacity to recover high-quality depth and orientation from specular objects.

Original language	English (US)
Title of host publication	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
DOIs	https://doi.org/10.1109/CVPR.2008.4587683
State	Published - 2008
Event	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR - Anchorage, AK, United States Duration: Jun 23 2008 → Jun 28 2008

Publication series

Name	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

Other

Other	26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Country/Territory	United States
City	Anchorage, AK
Period	6/23/08 → 6/28/08

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Control and Systems Engineering

Access to Document

10.1109/CVPR.2008.4587683

Cite this

@inproceedings{88e6d02ac49a4c0f8b74bb83b1dd468a,

title = "Dense 3D reconstruction from specularity consistency",

abstract = "In this work, we consider the dense reconstruction of specular objects. We propose the use of a specularity constraint, based on surface normal/depth consistency, to define a matching cost function that can drive standard stereo reconstruction methods. We discuss the types of ambiguity that can arise, and suggest an aggregation method based on anisotropic diffusion that is particularly suitable for this matching cost function. We also present a controlled illumination setup that includes a pair of cameras and one LCD monitor, which is used as a calibrated, variable-position light source. We use this setup to evaluate the proposed method on real data, and demonstrate its capacity to recover high-quality depth and orientation from specular objects.",

author = "Diego Nehab and Tim Weyrich and Szymon Rusinkiewicz",

year = "2008",

doi = "10.1109/CVPR.2008.4587683",

language = "English (US)",

isbn = "9781424422432",

series = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",

booktitle = "26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR",

}

Nehab, D, Weyrich, T & Rusinkiewicz, S 2008, Dense 3D reconstruction from specularity consistency. in 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR., 4587683, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Anchorage, AK, United States, 6/23/08. https://doi.org/10.1109/CVPR.2008.4587683

TY - GEN

T1 - Dense 3D reconstruction from specularity consistency

AU - Nehab, Diego

AU - Weyrich, Tim

AU - Rusinkiewicz, Szymon

PY - 2008

Y1 - 2008

N2 - In this work, we consider the dense reconstruction of specular objects. We propose the use of a specularity constraint, based on surface normal/depth consistency, to define a matching cost function that can drive standard stereo reconstruction methods. We discuss the types of ambiguity that can arise, and suggest an aggregation method based on anisotropic diffusion that is particularly suitable for this matching cost function. We also present a controlled illumination setup that includes a pair of cameras and one LCD monitor, which is used as a calibrated, variable-position light source. We use this setup to evaluate the proposed method on real data, and demonstrate its capacity to recover high-quality depth and orientation from specular objects.

AB - In this work, we consider the dense reconstruction of specular objects. We propose the use of a specularity constraint, based on surface normal/depth consistency, to define a matching cost function that can drive standard stereo reconstruction methods. We discuss the types of ambiguity that can arise, and suggest an aggregation method based on anisotropic diffusion that is particularly suitable for this matching cost function. We also present a controlled illumination setup that includes a pair of cameras and one LCD monitor, which is used as a calibrated, variable-position light source. We use this setup to evaluate the proposed method on real data, and demonstrate its capacity to recover high-quality depth and orientation from specular objects.

UR - http://www.scopus.com/inward/record.url?scp=51949092145&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51949092145&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2008.4587683

DO - 10.1109/CVPR.2008.4587683

M3 - Conference contribution

AN - SCOPUS:51949092145

SN - 9781424422432

T3 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

BT - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

T2 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR

Y2 - 23 June 2008 through 28 June 2008

ER -

Dense 3D reconstruction from specularity consistency

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this