Capturing and animating occluded cloth

Ryan White, Keenan Crane, David Alexander Forsyth

Research output: Contribution to journalArticle

Abstract

We capture the shape of moving cloth using a custom set of color markers printed on the surface of the cloth. The output is a sequence of triangle meshes with static connectivity and with detail at the scale of individual markers in both smooth and folded regions. We compute markers' coordinates in space using correspondence across multiple synchronized video cameras. Correspondence is determined from color information in small neighborhoods and refined using a novel strain pruning process. Final correspondence does not require neighborhood information. We use a novel data driven hole-filling technique to fill occluded regions. Our results include several challenging examples: a wrinkled shirt sleeve, a dancing pair of pants, and a rag tossed onto a cup. Finally, we demonstrate that cloth capture is reusable by animating a pair of pants using human motion capture data.

Original languageEnglish (US)
Article number1276420
JournalACM Transactions on Graphics
Volume26
Issue number3
DOIs
StatePublished - Jul 29 2007

Fingerprint

Color
Video cameras
Data acquisition

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Cite this

Capturing and animating occluded cloth. / White, Ryan; Crane, Keenan; Forsyth, David Alexander.

In: ACM Transactions on Graphics, Vol. 26, No. 3, 1276420, 29.07.2007.

Research output: Contribution to journalArticle

@article{44133b9e16744287a79f06c1e37b2bb0,
title = "Capturing and animating occluded cloth",
abstract = "We capture the shape of moving cloth using a custom set of color markers printed on the surface of the cloth. The output is a sequence of triangle meshes with static connectivity and with detail at the scale of individual markers in both smooth and folded regions. We compute markers' coordinates in space using correspondence across multiple synchronized video cameras. Correspondence is determined from color information in small neighborhoods and refined using a novel strain pruning process. Final correspondence does not require neighborhood information. We use a novel data driven hole-filling technique to fill occluded regions. Our results include several challenging examples: a wrinkled shirt sleeve, a dancing pair of pants, and a rag tossed onto a cup. Finally, we demonstrate that cloth capture is reusable by animating a pair of pants using human motion capture data.",
author = "Ryan White and Keenan Crane and Forsyth, {David Alexander}",
year = "2007",
month = "7",
day = "29",
doi = "10.1145/1276377.1276420",
language = "English (US)",
volume = "26",
journal = "ACM Transactions on Computer Systems",
issn = "0730-0301",
publisher = "Association for Computing Machinery (ACM)",
number = "3",

}

TY - JOUR

T1 - Capturing and animating occluded cloth

AU - White, Ryan

AU - Crane, Keenan

AU - Forsyth, David Alexander

PY - 2007/7/29

Y1 - 2007/7/29

N2 - We capture the shape of moving cloth using a custom set of color markers printed on the surface of the cloth. The output is a sequence of triangle meshes with static connectivity and with detail at the scale of individual markers in both smooth and folded regions. We compute markers' coordinates in space using correspondence across multiple synchronized video cameras. Correspondence is determined from color information in small neighborhoods and refined using a novel strain pruning process. Final correspondence does not require neighborhood information. We use a novel data driven hole-filling technique to fill occluded regions. Our results include several challenging examples: a wrinkled shirt sleeve, a dancing pair of pants, and a rag tossed onto a cup. Finally, we demonstrate that cloth capture is reusable by animating a pair of pants using human motion capture data.

AB - We capture the shape of moving cloth using a custom set of color markers printed on the surface of the cloth. The output is a sequence of triangle meshes with static connectivity and with detail at the scale of individual markers in both smooth and folded regions. We compute markers' coordinates in space using correspondence across multiple synchronized video cameras. Correspondence is determined from color information in small neighborhoods and refined using a novel strain pruning process. Final correspondence does not require neighborhood information. We use a novel data driven hole-filling technique to fill occluded regions. Our results include several challenging examples: a wrinkled shirt sleeve, a dancing pair of pants, and a rag tossed onto a cup. Finally, we demonstrate that cloth capture is reusable by animating a pair of pants using human motion capture data.

UR - http://www.scopus.com/inward/record.url?scp=34547699177&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547699177&partnerID=8YFLogxK

U2 - 10.1145/1276377.1276420

DO - 10.1145/1276377.1276420

M3 - Article

AN - SCOPUS:34547699177

VL - 26

JO - ACM Transactions on Computer Systems

JF - ACM Transactions on Computer Systems

SN - 0730-0301

IS - 3

M1 - 1276420

ER -