Texture overlay onto non-rigid surface using commodity depth camera

Tomoki Hayashi, Francois De Sorbier, Hideo Saito

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

8 Citations (Scopus)

Abstract

We present a method for overlaying a texture onto a non-rigid surface using a commodity depth camera. The depth cameras are able to capture 3-D data of a surface in real-time, and have several advantages compared with methods using only standard color cameras. However, it is not easy to register a 3-D deformable mesh to a point cloud of the non-rigid surface while keeping its geometrical topology. In order to solve this problem, our method starts by learning many representative meshes to generate surface deformation models. Then, while capturing 3-D data, we register a feasible 3-D mesh to the target surface and overlay a template texture onto the registered mesh. Even if the depth data are noisy or sparse, the learning-based method provides us with a smooth surface mesh. In addition, our method can be applied to real-time applications. In our experiments, we show some augmented reality results of texture overlay onto a non-textured T-shirt.

Original languageEnglish
Title of host publicationVISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications
Pages66-71
Number of pages6
Volume2
Publication statusPublished - 2012
EventInternational Conference on Computer Vision Theory and Applications, VISAPP 2012 - Rome, Italy
Duration: 2012 Feb 242012 Feb 26

Other

OtherInternational Conference on Computer Vision Theory and Applications, VISAPP 2012
CountryItaly
CityRome
Period12/2/2412/2/26

Fingerprint

Textures
Cameras
Augmented reality
Topology
Color
Experiments

Keywords

  • Augmented reality
  • Deformable 3-D registration
  • Depth camera
  • Principal component analysis

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Hayashi, T., De Sorbier, F., & Saito, H. (2012). Texture overlay onto non-rigid surface using commodity depth camera. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications (Vol. 2, pp. 66-71)

Texture overlay onto non-rigid surface using commodity depth camera. / Hayashi, Tomoki; De Sorbier, Francois; Saito, Hideo.

VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 2 2012. p. 66-71.

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

Hayashi, T, De Sorbier, F & Saito, H 2012, Texture overlay onto non-rigid surface using commodity depth camera. in VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. vol. 2, pp. 66-71, International Conference on Computer Vision Theory and Applications, VISAPP 2012, Rome, Italy, 12/2/24.
Hayashi T, De Sorbier F, Saito H. Texture overlay onto non-rigid surface using commodity depth camera. In VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 2. 2012. p. 66-71
Hayashi, Tomoki ; De Sorbier, Francois ; Saito, Hideo. / Texture overlay onto non-rigid surface using commodity depth camera. VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications. Vol. 2 2012. pp. 66-71
@inproceedings{3da033a15cb0480496b793374b92b919,
title = "Texture overlay onto non-rigid surface using commodity depth camera",
abstract = "We present a method for overlaying a texture onto a non-rigid surface using a commodity depth camera. The depth cameras are able to capture 3-D data of a surface in real-time, and have several advantages compared with methods using only standard color cameras. However, it is not easy to register a 3-D deformable mesh to a point cloud of the non-rigid surface while keeping its geometrical topology. In order to solve this problem, our method starts by learning many representative meshes to generate surface deformation models. Then, while capturing 3-D data, we register a feasible 3-D mesh to the target surface and overlay a template texture onto the registered mesh. Even if the depth data are noisy or sparse, the learning-based method provides us with a smooth surface mesh. In addition, our method can be applied to real-time applications. In our experiments, we show some augmented reality results of texture overlay onto a non-textured T-shirt.",
keywords = "Augmented reality, Deformable 3-D registration, Depth camera, Principal component analysis",
author = "Tomoki Hayashi and {De Sorbier}, Francois and Hideo Saito",
year = "2012",
language = "English",
isbn = "9789898565044",
volume = "2",
pages = "66--71",
booktitle = "VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications",

}

TY - GEN

T1 - Texture overlay onto non-rigid surface using commodity depth camera

AU - Hayashi, Tomoki

AU - De Sorbier, Francois

AU - Saito, Hideo

PY - 2012

Y1 - 2012

N2 - We present a method for overlaying a texture onto a non-rigid surface using a commodity depth camera. The depth cameras are able to capture 3-D data of a surface in real-time, and have several advantages compared with methods using only standard color cameras. However, it is not easy to register a 3-D deformable mesh to a point cloud of the non-rigid surface while keeping its geometrical topology. In order to solve this problem, our method starts by learning many representative meshes to generate surface deformation models. Then, while capturing 3-D data, we register a feasible 3-D mesh to the target surface and overlay a template texture onto the registered mesh. Even if the depth data are noisy or sparse, the learning-based method provides us with a smooth surface mesh. In addition, our method can be applied to real-time applications. In our experiments, we show some augmented reality results of texture overlay onto a non-textured T-shirt.

AB - We present a method for overlaying a texture onto a non-rigid surface using a commodity depth camera. The depth cameras are able to capture 3-D data of a surface in real-time, and have several advantages compared with methods using only standard color cameras. However, it is not easy to register a 3-D deformable mesh to a point cloud of the non-rigid surface while keeping its geometrical topology. In order to solve this problem, our method starts by learning many representative meshes to generate surface deformation models. Then, while capturing 3-D data, we register a feasible 3-D mesh to the target surface and overlay a template texture onto the registered mesh. Even if the depth data are noisy or sparse, the learning-based method provides us with a smooth surface mesh. In addition, our method can be applied to real-time applications. In our experiments, we show some augmented reality results of texture overlay onto a non-textured T-shirt.

KW - Augmented reality

KW - Deformable 3-D registration

KW - Depth camera

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=84862154874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862154874&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84862154874

SN - 9789898565044

VL - 2

SP - 66

EP - 71

BT - VISAPP 2012 - Proceedings of the International Conference on Computer Vision Theory and Applications

ER -