Surface Reconstruction from 3D Line Segments

Pierre Alain Langlois; Alexandre Boulch; Renaud Marlet

doi:10.1109/3DV.2019.00067

Surface Reconstruction from 3D Line Segments

Pierre Alain Langlois, Alexandre Boulch, Renaud Marlet

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

Abstract

In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input data, noise and outliers.

Original language	English
Title of host publication	Proceedings - 2019 International Conference on 3D Vision, 3DV 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	553-563
Number of pages	11
ISBN (Electronic)	9781728131313
DOIs	https://doi.org/10.1109/3DV.2019.00067
Publication status	Published - 1 Sept 2019
Externally published	Yes
Event	7th International Conference on 3D Vision, 3DV 2019 - Quebec, Canada Duration: 15 Sept 2019 → 18 Sept 2019

Publication series

Name	Proceedings - 2019 International Conference on 3D Vision, 3DV 2019

Conference

Conference	7th International Conference on 3D Vision, 3DV 2019
Country/Territory	Canada
City	Quebec
Period	15/09/19 → 18/09/19

Keywords

line
multi view
photogrammetry
piecewise planar
reconstruction
watertight

Access to Document

10.1109/3DV.2019.00067

Cite this

@inproceedings{f7b3caec63364357874a9874c93ad91a,

title = "Surface Reconstruction from 3D Line Segments",

abstract = "In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input data, noise and outliers.",

keywords = "line, multi view, photogrammetry, piecewise planar, reconstruction, watertight",

author = "Langlois, \{Pierre Alain\} and Alexandre Boulch and Renaud Marlet",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 7th International Conference on 3D Vision, 3DV 2019 ; Conference date: 15-09-2019 Through 18-09-2019",

year = "2019",

month = sep,

day = "1",

doi = "10.1109/3DV.2019.00067",

language = "English",

series = "Proceedings - 2019 International Conference on 3D Vision, 3DV 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "553--563",

booktitle = "Proceedings - 2019 International Conference on 3D Vision, 3DV 2019",

}

Langlois, PA, Boulch, A & Marlet, R 2019, Surface Reconstruction from 3D Line Segments. in Proceedings - 2019 International Conference on 3D Vision, 3DV 2019., 8885913, Proceedings - 2019 International Conference on 3D Vision, 3DV 2019, Institute of Electrical and Electronics Engineers Inc., pp. 553-563, 7th International Conference on 3D Vision, 3DV 2019, Quebec, Canada, 15/09/19. https://doi.org/10.1109/3DV.2019.00067

Surface Reconstruction from 3D Line Segments. / Langlois, Pierre Alain; Boulch, Alexandre; Marlet, Renaud.
Proceedings - 2019 International Conference on 3D Vision, 3DV 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 553-563 8885913 (Proceedings - 2019 International Conference on 3D Vision, 3DV 2019).

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

TY - GEN

T1 - Surface Reconstruction from 3D Line Segments

AU - Langlois, Pierre Alain

AU - Boulch, Alexandre

AU - Marlet, Renaud

PY - 2019/9/1

Y1 - 2019/9/1

N2 - In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input data, noise and outliers.

AB - In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input data, noise and outliers.

KW - line

KW - multi view

KW - photogrammetry

KW - piecewise planar

KW - reconstruction

KW - watertight

UR - https://www.scopus.com/pages/publications/85075012218

U2 - 10.1109/3DV.2019.00067

DO - 10.1109/3DV.2019.00067

M3 - Conference contribution

AN - SCOPUS:85075012218

T3 - Proceedings - 2019 International Conference on 3D Vision, 3DV 2019

SP - 553

EP - 563

BT - Proceedings - 2019 International Conference on 3D Vision, 3DV 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Conference on 3D Vision, 3DV 2019

Y2 - 15 September 2019 through 18 September 2019

ER -

Surface Reconstruction from 3D Line Segments

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this