SDG cut: 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid

Tianli Yu; Narendra Ahuja; Wei Chao Chen

doi:10.1109/CVPR.2006.267

SDG cut: 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid

Tianli Yu, Narendra Ahuja, Wei Chao Chen

Beckman Institute for Advanced Science and Technology

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

Abstract

We show that the approaches to 3D reconstruction that use volumetric graph cuts to minimize a cost function over the object surface have two types of biases, the minimal surface bias and the discretization bias. These biases make it difficult to recover surface extrusions and other details, especially when a non-lambertian photo-consistency measure is used. To reduce these biases, we propose a new iterative graph cuts based algorithm that operates on the Surface Distance Grid (SDG), which is a special discretization of the 3D space, constructed using a signed distance transform of the current surface estimate. It can be shown that SDG significantly reduces the minimal surface bias, and transforms the discretization bias into a controllable degree of surface smoothness. Experiments on 3D reconstruction of non-lambertian objects confirm the effectiveness of our algorithm over previous methods.

Original language	English (US)
Title of host publication	Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages	2269-2276
Number of pages	8
DOIs	https://doi.org/10.1109/CVPR.2006.267
State	Published - 2006
Event	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States Duration: Jun 17 2006 → Jun 22 2006

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2
ISSN (Print)	1063-6919

Other

Other	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Country	United States
City	New York, NY
Period	6/17/06 → 6/22/06

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2006.267

Fingerprint Dive into the research topics of 'SDG cut: 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid'. Together they form a unique fingerprint.

Cite this

Yu, T., Ahuja, N., & Chen, W. C. (2006). SDG cut: 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 (pp. 2269-2276). [1641031] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2). https://doi.org/10.1109/CVPR.2006.267

SDG cut : 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid. / Yu, Tianli; Ahuja, Narendra; Chen, Wei Chao.

Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 2269-2276 1641031 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2).

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

Yu, T, Ahuja, N & Chen, WC 2006, SDG cut: 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid. in Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006., 1641031, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2269-2276, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, NY, United States, 6/17/06. https://doi.org/10.1109/CVPR.2006.267

Yu T, Ahuja N, Chen WC. SDG cut: 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 2269-2276. 1641031. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2006.267

Yu, Tianli ; Ahuja, Narendra ; Chen, Wei Chao. / SDG cut : 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid. Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. pp. 2269-2276 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

@inproceedings{8894b8508c92400a85ddab7cde438181,

title = "SDG cut: 3D reconstruction of non-lambertian objects using graph cuts on surface distance grid",

abstract = "We show that the approaches to 3D reconstruction that use volumetric graph cuts to minimize a cost function over the object surface have two types of biases, the minimal surface bias and the discretization bias. These biases make it difficult to recover surface extrusions and other details, especially when a non-lambertian photo-consistency measure is used. To reduce these biases, we propose a new iterative graph cuts based algorithm that operates on the Surface Distance Grid (SDG), which is a special discretization of the 3D space, constructed using a signed distance transform of the current surface estimate. It can be shown that SDG significantly reduces the minimal surface bias, and transforms the discretization bias into a controllable degree of surface smoothness. Experiments on 3D reconstruction of non-lambertian objects confirm the effectiveness of our algorithm over previous methods.",

author = "Tianli Yu and Narendra Ahuja and Chen, {Wei Chao}",

note = "Copyright: Copyright 2011 Elsevier B.V., All rights reserved.; 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 ; Conference date: 17-06-2006 Through 22-06-2006",

year = "2006",

doi = "10.1109/CVPR.2006.267",

language = "English (US)",

isbn = "0769525970",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

pages = "2269--2276",

booktitle = "Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006",

}

TY - GEN

T1 - SDG cut

T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

AU - Yu, Tianli

AU - Ahuja, Narendra

AU - Chen, Wei Chao

PY - 2006

Y1 - 2006

N2 - We show that the approaches to 3D reconstruction that use volumetric graph cuts to minimize a cost function over the object surface have two types of biases, the minimal surface bias and the discretization bias. These biases make it difficult to recover surface extrusions and other details, especially when a non-lambertian photo-consistency measure is used. To reduce these biases, we propose a new iterative graph cuts based algorithm that operates on the Surface Distance Grid (SDG), which is a special discretization of the 3D space, constructed using a signed distance transform of the current surface estimate. It can be shown that SDG significantly reduces the minimal surface bias, and transforms the discretization bias into a controllable degree of surface smoothness. Experiments on 3D reconstruction of non-lambertian objects confirm the effectiveness of our algorithm over previous methods.

AB - We show that the approaches to 3D reconstruction that use volumetric graph cuts to minimize a cost function over the object surface have two types of biases, the minimal surface bias and the discretization bias. These biases make it difficult to recover surface extrusions and other details, especially when a non-lambertian photo-consistency measure is used. To reduce these biases, we propose a new iterative graph cuts based algorithm that operates on the Surface Distance Grid (SDG), which is a special discretization of the 3D space, constructed using a signed distance transform of the current surface estimate. It can be shown that SDG significantly reduces the minimal surface bias, and transforms the discretization bias into a controllable degree of surface smoothness. Experiments on 3D reconstruction of non-lambertian objects confirm the effectiveness of our algorithm over previous methods.

UR - http://www.scopus.com/inward/record.url?scp=33845595946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845595946&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2006.267

DO - 10.1109/CVPR.2006.267

M3 - Conference contribution

AN - SCOPUS:33845595946

SN - 0769525970

SN - 9780769525976

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 2269

EP - 2276

BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

Y2 - 17 June 2006 through 22 June 2006

ER -