Texture overlay for virtual clothing based on PCA of silhouettes

Jun Ehara, Hideo Saito

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

23 Citations (Scopus)

Abstract

In this paper, we propose a method for overlaying an arbitrary texture image onto a surface of a plain T-shirt worn by a user. For overlaying arbitrary textures onto the surface of the T-shirt, we need to know the deformation of the surface. For estimating the deformation of the surface from the input images, we use a two-phase process: learning and searching. In the learning phase, the system learns the relationship between the deformation of the surface and the silhouette of the T-shirt region in the image. A database of a number of training images in which a person wearing a T-shirt with markers moves through a variety of positions is used for this learning. Using the database, the system can learn the relationship between the shape of the silhouette and the surface deformation that is provided by the 2D positions of the markers on the surface of the T-shirt. In the searching phase, the silhouette of the user's T-shirt is extracted from the input image, and then, a search for a similar silhouette in the database is conducted in the subspace of the silhouette, which is computed using a PCA of the database. By using the proposed method for estimating the deformation of the surface of the T-shirt, we perform experiments for overlaying virtual clothing.

Original languageEnglish
Title of host publicationProceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality
Pages139-142
Number of pages4
DOIs
Publication statusPublished - 2007
EventISMAR 2006: 5th IEEE and ACM International Symposium on Mixed and Augmented Reality - Santa Barbara, CA, United States
Duration: 2006 Oct 222006 Oct 25

Other

OtherISMAR 2006: 5th IEEE and ACM International Symposium on Mixed and Augmented Reality
CountryUnited States
CitySanta Barbara, CA
Period06/10/2206/10/25

Fingerprint

Textures
Experiments

Keywords

  • Augmented reality
  • Deformable surface
  • Learning
  • PCA
  • Silhouette
  • Texture mapping
  • Virtual clothing

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Ehara, J., & Saito, H. (2007). Texture overlay for virtual clothing based on PCA of silhouettes. In Proceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality (pp. 139-142). [4079267] https://doi.org/10.1109/ISMAR.2006.297805

Texture overlay for virtual clothing based on PCA of silhouettes. / Ehara, Jun; Saito, Hideo.

Proceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality. 2007. p. 139-142 4079267.

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

Ehara, J & Saito, H 2007, Texture overlay for virtual clothing based on PCA of silhouettes. in Proceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality., 4079267, pp. 139-142, ISMAR 2006: 5th IEEE and ACM International Symposium on Mixed and Augmented Reality, Santa Barbara, CA, United States, 06/10/22. https://doi.org/10.1109/ISMAR.2006.297805
Ehara J, Saito H. Texture overlay for virtual clothing based on PCA of silhouettes. In Proceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality. 2007. p. 139-142. 4079267 https://doi.org/10.1109/ISMAR.2006.297805
Ehara, Jun ; Saito, Hideo. / Texture overlay for virtual clothing based on PCA of silhouettes. Proceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality. 2007. pp. 139-142
@inproceedings{271e6e6967ee4a8386eff2854c109dd7,
title = "Texture overlay for virtual clothing based on PCA of silhouettes",
abstract = "In this paper, we propose a method for overlaying an arbitrary texture image onto a surface of a plain T-shirt worn by a user. For overlaying arbitrary textures onto the surface of the T-shirt, we need to know the deformation of the surface. For estimating the deformation of the surface from the input images, we use a two-phase process: learning and searching. In the learning phase, the system learns the relationship between the deformation of the surface and the silhouette of the T-shirt region in the image. A database of a number of training images in which a person wearing a T-shirt with markers moves through a variety of positions is used for this learning. Using the database, the system can learn the relationship between the shape of the silhouette and the surface deformation that is provided by the 2D positions of the markers on the surface of the T-shirt. In the searching phase, the silhouette of the user's T-shirt is extracted from the input image, and then, a search for a similar silhouette in the database is conducted in the subspace of the silhouette, which is computed using a PCA of the database. By using the proposed method for estimating the deformation of the surface of the T-shirt, we perform experiments for overlaying virtual clothing.",
keywords = "Augmented reality, Deformable surface, Learning, PCA, Silhouette, Texture mapping, Virtual clothing",
author = "Jun Ehara and Hideo Saito",
year = "2007",
doi = "10.1109/ISMAR.2006.297805",
language = "English",
isbn = "1424406501",
pages = "139--142",
booktitle = "Proceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality",

}

TY - GEN

T1 - Texture overlay for virtual clothing based on PCA of silhouettes

AU - Ehara, Jun

AU - Saito, Hideo

PY - 2007

Y1 - 2007

N2 - In this paper, we propose a method for overlaying an arbitrary texture image onto a surface of a plain T-shirt worn by a user. For overlaying arbitrary textures onto the surface of the T-shirt, we need to know the deformation of the surface. For estimating the deformation of the surface from the input images, we use a two-phase process: learning and searching. In the learning phase, the system learns the relationship between the deformation of the surface and the silhouette of the T-shirt region in the image. A database of a number of training images in which a person wearing a T-shirt with markers moves through a variety of positions is used for this learning. Using the database, the system can learn the relationship between the shape of the silhouette and the surface deformation that is provided by the 2D positions of the markers on the surface of the T-shirt. In the searching phase, the silhouette of the user's T-shirt is extracted from the input image, and then, a search for a similar silhouette in the database is conducted in the subspace of the silhouette, which is computed using a PCA of the database. By using the proposed method for estimating the deformation of the surface of the T-shirt, we perform experiments for overlaying virtual clothing.

AB - In this paper, we propose a method for overlaying an arbitrary texture image onto a surface of a plain T-shirt worn by a user. For overlaying arbitrary textures onto the surface of the T-shirt, we need to know the deformation of the surface. For estimating the deformation of the surface from the input images, we use a two-phase process: learning and searching. In the learning phase, the system learns the relationship between the deformation of the surface and the silhouette of the T-shirt region in the image. A database of a number of training images in which a person wearing a T-shirt with markers moves through a variety of positions is used for this learning. Using the database, the system can learn the relationship between the shape of the silhouette and the surface deformation that is provided by the 2D positions of the markers on the surface of the T-shirt. In the searching phase, the silhouette of the user's T-shirt is extracted from the input image, and then, a search for a similar silhouette in the database is conducted in the subspace of the silhouette, which is computed using a PCA of the database. By using the proposed method for estimating the deformation of the surface of the T-shirt, we perform experiments for overlaying virtual clothing.

KW - Augmented reality

KW - Deformable surface

KW - Learning

KW - PCA

KW - Silhouette

KW - Texture mapping

KW - Virtual clothing

UR - http://www.scopus.com/inward/record.url?scp=45149115472&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=45149115472&partnerID=8YFLogxK

U2 - 10.1109/ISMAR.2006.297805

DO - 10.1109/ISMAR.2006.297805

M3 - Conference contribution

AN - SCOPUS:45149115472

SN - 1424406501

SN - 9781424406500

SP - 139

EP - 142

BT - Proceedings - ISMAR 2006: Fifth IEEE and ACM International Symposium on Mixed and Augmented Reality

ER -