Parametric Surface Representation with Bump Image for Dense 3D Modeling Using an RBG-D Camera

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

When constructing a dense 3D model of an indoor static scene from a sequence of RGB-D images, the choice of the 3D representation (e.g. 3D mesh, cloud of points or implicit function) is of crucial importance. In the last few years, the volumetric truncated signed distance function (TSDF) and its extensions have become popular in the community and largely used for the task of dense 3D modelling using RGB-D sensors. However, as this representation is voxel based, it offers few possibilities for manipulating and/or editing the constructed 3D model, which limits its applicability. In particular, the amount of data required to maintain the volumetric TSDF rapidly becomes huge which limits possibilities for portability. Moreover, simplifications (such as mesh extraction and surface simplification) significantly reduce the accuracy of the 3D model (especially in the color space), and editing the 3D model is difficult. We propose a novel compact, flexible and accurate 3D surface representation based on parametric surface patches augmented by geometric and color texture images. Simple parametric shapes such as planes are roughly fitted to the input depth images, and the deviations of the 3D measurements to the fitted parametric surfaces are fused into a geometric texture image (called the Bump image). A confidence and color texture image are also built. Our 3D scene representation is accurate yet memory efficient. Moreover, updating or editing the 3D model becomes trivial since it is reduced to manipulating 2D images. Our experimental results demonstrate the advantages of our proposed 3D representation through a concrete indoor scene reconstruction application.

Original languageEnglish
Pages (from-to)1-20
Number of pages20
JournalInternational Journal of Computer Vision
Volume123
Issue number2
DOIs
Publication statusPublished - Jun 1 2017

Fingerprint

Cameras
Textures
Color
Concretes
Data storage equipment
Sensors

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Parametric Surface Representation with Bump Image for Dense 3D Modeling Using an RBG-D Camera. / Thomas, Diego Gabriel Francis; Sugimoto, Akihiro.

In: International Journal of Computer Vision, Vol. 123, No. 2, 01.06.2017, p. 1-20.

Research output: Contribution to journalArticle

@article{197f11be92aa4e12b431861e1b739267,
title = "Parametric Surface Representation with Bump Image for Dense 3D Modeling Using an RBG-D Camera",
abstract = "When constructing a dense 3D model of an indoor static scene from a sequence of RGB-D images, the choice of the 3D representation (e.g. 3D mesh, cloud of points or implicit function) is of crucial importance. In the last few years, the volumetric truncated signed distance function (TSDF) and its extensions have become popular in the community and largely used for the task of dense 3D modelling using RGB-D sensors. However, as this representation is voxel based, it offers few possibilities for manipulating and/or editing the constructed 3D model, which limits its applicability. In particular, the amount of data required to maintain the volumetric TSDF rapidly becomes huge which limits possibilities for portability. Moreover, simplifications (such as mesh extraction and surface simplification) significantly reduce the accuracy of the 3D model (especially in the color space), and editing the 3D model is difficult. We propose a novel compact, flexible and accurate 3D surface representation based on parametric surface patches augmented by geometric and color texture images. Simple parametric shapes such as planes are roughly fitted to the input depth images, and the deviations of the 3D measurements to the fitted parametric surfaces are fused into a geometric texture image (called the Bump image). A confidence and color texture image are also built. Our 3D scene representation is accurate yet memory efficient. Moreover, updating or editing the 3D model becomes trivial since it is reduced to manipulating 2D images. Our experimental results demonstrate the advantages of our proposed 3D representation through a concrete indoor scene reconstruction application.",
author = "Thomas, {Diego Gabriel Francis} and Akihiro Sugimoto",
year = "2017",
month = "6",
day = "1",
doi = "10.1007/s11263-016-0969-3",
language = "English",
volume = "123",
pages = "1--20",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Parametric Surface Representation with Bump Image for Dense 3D Modeling Using an RBG-D Camera

AU - Thomas, Diego Gabriel Francis

AU - Sugimoto, Akihiro

PY - 2017/6/1

Y1 - 2017/6/1

N2 - When constructing a dense 3D model of an indoor static scene from a sequence of RGB-D images, the choice of the 3D representation (e.g. 3D mesh, cloud of points or implicit function) is of crucial importance. In the last few years, the volumetric truncated signed distance function (TSDF) and its extensions have become popular in the community and largely used for the task of dense 3D modelling using RGB-D sensors. However, as this representation is voxel based, it offers few possibilities for manipulating and/or editing the constructed 3D model, which limits its applicability. In particular, the amount of data required to maintain the volumetric TSDF rapidly becomes huge which limits possibilities for portability. Moreover, simplifications (such as mesh extraction and surface simplification) significantly reduce the accuracy of the 3D model (especially in the color space), and editing the 3D model is difficult. We propose a novel compact, flexible and accurate 3D surface representation based on parametric surface patches augmented by geometric and color texture images. Simple parametric shapes such as planes are roughly fitted to the input depth images, and the deviations of the 3D measurements to the fitted parametric surfaces are fused into a geometric texture image (called the Bump image). A confidence and color texture image are also built. Our 3D scene representation is accurate yet memory efficient. Moreover, updating or editing the 3D model becomes trivial since it is reduced to manipulating 2D images. Our experimental results demonstrate the advantages of our proposed 3D representation through a concrete indoor scene reconstruction application.

AB - When constructing a dense 3D model of an indoor static scene from a sequence of RGB-D images, the choice of the 3D representation (e.g. 3D mesh, cloud of points or implicit function) is of crucial importance. In the last few years, the volumetric truncated signed distance function (TSDF) and its extensions have become popular in the community and largely used for the task of dense 3D modelling using RGB-D sensors. However, as this representation is voxel based, it offers few possibilities for manipulating and/or editing the constructed 3D model, which limits its applicability. In particular, the amount of data required to maintain the volumetric TSDF rapidly becomes huge which limits possibilities for portability. Moreover, simplifications (such as mesh extraction and surface simplification) significantly reduce the accuracy of the 3D model (especially in the color space), and editing the 3D model is difficult. We propose a novel compact, flexible and accurate 3D surface representation based on parametric surface patches augmented by geometric and color texture images. Simple parametric shapes such as planes are roughly fitted to the input depth images, and the deviations of the 3D measurements to the fitted parametric surfaces are fused into a geometric texture image (called the Bump image). A confidence and color texture image are also built. Our 3D scene representation is accurate yet memory efficient. Moreover, updating or editing the 3D model becomes trivial since it is reduced to manipulating 2D images. Our experimental results demonstrate the advantages of our proposed 3D representation through a concrete indoor scene reconstruction application.

UR - http://www.scopus.com/inward/record.url?scp=85046235949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046235949&partnerID=8YFLogxK

U2 - 10.1007/s11263-016-0969-3

DO - 10.1007/s11263-016-0969-3

M3 - Article

VL - 123

SP - 1

EP - 20

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 2

ER -