Image guided geometry inference

Songhua Xu; Athinodoros Georghiades; Holly Rushmeier; Julie Dorsey; Leonard McMillan

doi:10.1109/3DPVT.2006.81

Image guided geometry inference

Songhua Xu, Athinodoros Georghiades, Holly Rushmeier, Julie Dorsey, Leonard McMillan

Informatics

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

15 Scopus citations

Abstract

We introduce a new method for filling holes in geometry obtained from 3D range scanners. Our method makes use of 2D images of the areas where geometric data is missing. The 2D images guide the filling using the relationship between the images and geometry learned from the existing 3D scanned data. Our method builds on existing techniques for using scanned geometry and for estimating shape from shaded images. Rather than creating plausibly filled holes, we attempt to approximate the missing geometry. We present results for scanned data from both triangulation and time-of-flight scanners for various types of materials. To quantitatively validate our proposed method, we also compare the filled areas with ground-truth data.

Original language	English (US)
Title of host publication	Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Publisher	IEEE Computer Society
Pages	310-317
Number of pages	8
ISBN (Print)	0769528252, 9780769528250
DOIs	https://doi.org/10.1109/3DPVT.2006.81
State	Published - Jan 1 2006
Event	3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 - Chapel Hill, NC, United States Duration: Jun 14 2006 → Jun 16 2006

Publication series

Name	Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

Other

Other	3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Country/Territory	United States
City	Chapel Hill, NC
Period	6/14/06 → 6/16/06

All Science Journal Classification (ASJC) codes

Computer Graphics and Computer-Aided Design
Computer Networks and Communications

Access to Document

10.1109/3DPVT.2006.81

Cite this

Xu, S., Georghiades, A., Rushmeier, H., Dorsey, J., & McMillan, L. (2006). Image guided geometry inference. In Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 (pp. 310-317). Article 4155742 (Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006). IEEE Computer Society. https://doi.org/10.1109/3DPVT.2006.81

@inproceedings{071ddd90db1a4411a3532d41cb6d457b,

title = "Image guided geometry inference",

abstract = "We introduce a new method for filling holes in geometry obtained from 3D range scanners. Our method makes use of 2D images of the areas where geometric data is missing. The 2D images guide the filling using the relationship between the images and geometry learned from the existing 3D scanned data. Our method builds on existing techniques for using scanned geometry and for estimating shape from shaded images. Rather than creating plausibly filled holes, we attempt to approximate the missing geometry. We present results for scanned data from both triangulation and time-of-flight scanners for various types of materials. To quantitatively validate our proposed method, we also compare the filled areas with ground-truth data.",

author = "Songhua Xu and Athinodoros Georghiades and Holly Rushmeier and Julie Dorsey and Leonard McMillan",

year = "2006",

month = jan,

day = "1",

doi = "10.1109/3DPVT.2006.81",

language = "English (US)",

isbn = "0769528252",

series = "Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006",

publisher = "IEEE Computer Society",

pages = "310--317",

booktitle = "Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006",

address = "United States",

note = "3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 ; Conference date: 14-06-2006 Through 16-06-2006",

}

Xu, S, Georghiades, A, Rushmeier, H, Dorsey, J & McMillan, L 2006, Image guided geometry inference. in Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006., 4155742, Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006, IEEE Computer Society, pp. 310-317, 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006, Chapel Hill, NC, United States, 6/14/06. https://doi.org/10.1109/3DPVT.2006.81

Image guided geometry inference. / Xu, Songhua; Georghiades, Athinodoros; Rushmeier, Holly et al.
Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. IEEE Computer Society, 2006. p. 310-317 4155742 (Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006).

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

TY - GEN

T1 - Image guided geometry inference

AU - Xu, Songhua

AU - Georghiades, Athinodoros

AU - Rushmeier, Holly

AU - Dorsey, Julie

AU - McMillan, Leonard

PY - 2006/1/1

Y1 - 2006/1/1

N2 - We introduce a new method for filling holes in geometry obtained from 3D range scanners. Our method makes use of 2D images of the areas where geometric data is missing. The 2D images guide the filling using the relationship between the images and geometry learned from the existing 3D scanned data. Our method builds on existing techniques for using scanned geometry and for estimating shape from shaded images. Rather than creating plausibly filled holes, we attempt to approximate the missing geometry. We present results for scanned data from both triangulation and time-of-flight scanners for various types of materials. To quantitatively validate our proposed method, we also compare the filled areas with ground-truth data.

AB - We introduce a new method for filling holes in geometry obtained from 3D range scanners. Our method makes use of 2D images of the areas where geometric data is missing. The 2D images guide the filling using the relationship between the images and geometry learned from the existing 3D scanned data. Our method builds on existing techniques for using scanned geometry and for estimating shape from shaded images. Rather than creating plausibly filled holes, we attempt to approximate the missing geometry. We present results for scanned data from both triangulation and time-of-flight scanners for various types of materials. To quantitatively validate our proposed method, we also compare the filled areas with ground-truth data.

UR - http://www.scopus.com/inward/record.url?scp=47249103454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47249103454&partnerID=8YFLogxK

U2 - 10.1109/3DPVT.2006.81

DO - 10.1109/3DPVT.2006.81

M3 - Conference contribution

SN - 0769528252

SN - 9780769528250

T3 - Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

SP - 310

EP - 317

BT - Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

PB - IEEE Computer Society

T2 - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

Y2 - 14 June 2006 through 16 June 2006

ER -

Xu S, Georghiades A, Rushmeier H, Dorsey J, McMillan L. Image guided geometry inference. In Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. IEEE Computer Society. 2006. p. 310-317. 4155742. (Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006). doi: 10.1109/3DPVT.2006.81

Image guided geometry inference

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this