Robust simultaneous 3D registration via rank minimization

Diego Gabriel Francis Thomas, Yasuyuki Matsushita, Akihiro Sugimoto

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

4 Citations (Scopus)

Abstract

We present a robust and accurate 3D registration method for a dense sequence of depth images taken from unknown viewpoints. Our method simultaneously estimates multiple extrinsic parameters of the depth images to obtain a registered full 3D model of the scanned scene. By arranging the depth measurements in a matrix form, we formulate the problem as a simultaneous estimation of multiple extrinsics and a low-rank matrix, which corresponds to the aligned depth images as well as a sparse error matrix. Unlike previous approaches that use sequential or heuristic global registration approaches, our solution method uses an advanced convex optimization technique for obtaining a robust solution via rank minimization. To achieve accurate computation, we develop a depth projection method that has minimum sensitivity to sampling by reading projected depth values in the input depth images. We demonstrate the effectiveness of the proposed method through extensive experiments and compare it with previous standard techniques.

Original languageEnglish
Title of host publicationProceedings - 2nd Joint 3DIM/3DPVT Conference
Subtitle of host publication3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012
Pages33-40
Number of pages8
DOIs
Publication statusPublished - Dec 1 2012
Event2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012 - Zurich, Switzerland
Duration: Oct 13 2012Oct 15 2012

Publication series

NameProceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012

Other

Other2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012
CountrySwitzerland
CityZurich
Period10/13/1210/15/12

Fingerprint

Registration
Convex optimization
Sampling
Low-rank Matrices
Simultaneous Estimation
Projection Method
Convex Optimization
3D Model
Optimization Techniques
Experiments
Heuristics
Unknown
Estimate
Demonstrate
Experiment

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Modelling and Simulation

Cite this

Thomas, D. G. F., Matsushita, Y., & Sugimoto, A. (2012). Robust simultaneous 3D registration via rank minimization. In Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012 (pp. 33-40). [6374974] (Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012). https://doi.org/10.1109/3DIMPVT.2012.15

Robust simultaneous 3D registration via rank minimization. / Thomas, Diego Gabriel Francis; Matsushita, Yasuyuki; Sugimoto, Akihiro.

Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012. 2012. p. 33-40 6374974 (Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012).

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

Thomas, DGF, Matsushita, Y & Sugimoto, A 2012, Robust simultaneous 3D registration via rank minimization. in Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012., 6374974, Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012, pp. 33-40, 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012, Zurich, Switzerland, 10/13/12. https://doi.org/10.1109/3DIMPVT.2012.15
Thomas DGF, Matsushita Y, Sugimoto A. Robust simultaneous 3D registration via rank minimization. In Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012. 2012. p. 33-40. 6374974. (Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012). https://doi.org/10.1109/3DIMPVT.2012.15
Thomas, Diego Gabriel Francis ; Matsushita, Yasuyuki ; Sugimoto, Akihiro. / Robust simultaneous 3D registration via rank minimization. Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012. 2012. pp. 33-40 (Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012).
@inproceedings{6a8c13f55e2c4612a8874f25d539f572,
title = "Robust simultaneous 3D registration via rank minimization",
abstract = "We present a robust and accurate 3D registration method for a dense sequence of depth images taken from unknown viewpoints. Our method simultaneously estimates multiple extrinsic parameters of the depth images to obtain a registered full 3D model of the scanned scene. By arranging the depth measurements in a matrix form, we formulate the problem as a simultaneous estimation of multiple extrinsics and a low-rank matrix, which corresponds to the aligned depth images as well as a sparse error matrix. Unlike previous approaches that use sequential or heuristic global registration approaches, our solution method uses an advanced convex optimization technique for obtaining a robust solution via rank minimization. To achieve accurate computation, we develop a depth projection method that has minimum sensitivity to sampling by reading projected depth values in the input depth images. We demonstrate the effectiveness of the proposed method through extensive experiments and compare it with previous standard techniques.",
author = "Thomas, {Diego Gabriel Francis} and Yasuyuki Matsushita and Akihiro Sugimoto",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/3DIMPVT.2012.15",
language = "English",
isbn = "9780769548739",
series = "Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012",
pages = "33--40",
booktitle = "Proceedings - 2nd Joint 3DIM/3DPVT Conference",

}

TY - GEN

T1 - Robust simultaneous 3D registration via rank minimization

AU - Thomas, Diego Gabriel Francis

AU - Matsushita, Yasuyuki

AU - Sugimoto, Akihiro

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We present a robust and accurate 3D registration method for a dense sequence of depth images taken from unknown viewpoints. Our method simultaneously estimates multiple extrinsic parameters of the depth images to obtain a registered full 3D model of the scanned scene. By arranging the depth measurements in a matrix form, we formulate the problem as a simultaneous estimation of multiple extrinsics and a low-rank matrix, which corresponds to the aligned depth images as well as a sparse error matrix. Unlike previous approaches that use sequential or heuristic global registration approaches, our solution method uses an advanced convex optimization technique for obtaining a robust solution via rank minimization. To achieve accurate computation, we develop a depth projection method that has minimum sensitivity to sampling by reading projected depth values in the input depth images. We demonstrate the effectiveness of the proposed method through extensive experiments and compare it with previous standard techniques.

AB - We present a robust and accurate 3D registration method for a dense sequence of depth images taken from unknown viewpoints. Our method simultaneously estimates multiple extrinsic parameters of the depth images to obtain a registered full 3D model of the scanned scene. By arranging the depth measurements in a matrix form, we formulate the problem as a simultaneous estimation of multiple extrinsics and a low-rank matrix, which corresponds to the aligned depth images as well as a sparse error matrix. Unlike previous approaches that use sequential or heuristic global registration approaches, our solution method uses an advanced convex optimization technique for obtaining a robust solution via rank minimization. To achieve accurate computation, we develop a depth projection method that has minimum sensitivity to sampling by reading projected depth values in the input depth images. We demonstrate the effectiveness of the proposed method through extensive experiments and compare it with previous standard techniques.

UR - http://www.scopus.com/inward/record.url?scp=84872050273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872050273&partnerID=8YFLogxK

U2 - 10.1109/3DIMPVT.2012.15

DO - 10.1109/3DIMPVT.2012.15

M3 - Conference contribution

AN - SCOPUS:84872050273

SN - 9780769548739

T3 - Proceedings - 2nd Joint 3DIM/3DPVT Conference: 3D Imaging, Modeling, Processing, Visualization and Transmission, 3DIMPVT 2012

SP - 33

EP - 40

BT - Proceedings - 2nd Joint 3DIM/3DPVT Conference

ER -