Modeling and generating moving trees from video

Chuan Li, Oliver Deussen, Yi-Zhe Song, Philip Willis, Peter Hall

Research output: Contribution to journalArticle

  • 24 Citations

Abstract

We present a probabilistic approach for the automatic production of tree models with convincing 3D appearance and motion. The only input is a video of a moving tree that provides us an initial dynamic tree model, which is used to generate new individual trees of the same type. Our approach combines global and local constraints to construct a dynamic 3D tree model from a 2D skeleton. Our modeling takes into account factors such as the shape of branches, the overall shape of the tree, and physically plausible motion. Furthermore, we provide a generative model that creates multiple trees in 3D, given a single example model. This means that users no longer have to make each tree individually, or specify rules to make new trees. Results with different species are presented and compared to both reference input data and state of the art alternatives.
LanguageEnglish
Article number127
Number of pages11
JournalACM Transactions on Graphics
Volume30
Issue number6
DOIs
StatusPublished - Dec 2011

Cite this

Li, C., Deussen, O., Song, Y-Z., Willis, P., & Hall, P. (2011). Modeling and generating moving trees from video. DOI: 10.1145/2024156.2024161

Modeling and generating moving trees from video. / Li, Chuan; Deussen, Oliver; Song, Yi-Zhe; Willis, Philip; Hall, Peter.

In: ACM Transactions on Graphics, Vol. 30, No. 6, 127, 12.2011.

Research output: Contribution to journalArticle

Li, C, Deussen, O, Song, Y-Z, Willis, P & Hall, P 2011, 'Modeling and generating moving trees from video' ACM Transactions on Graphics, vol. 30, no. 6, 127. DOI: 10.1145/2024156.2024161
Li C, Deussen O, Song Y-Z, Willis P, Hall P. Modeling and generating moving trees from video. ACM Transactions on Graphics. 2011 Dec;30(6). 127. Available from, DOI: 10.1145/2024156.2024161
Li, Chuan ; Deussen, Oliver ; Song, Yi-Zhe ; Willis, Philip ; Hall, Peter. / Modeling and generating moving trees from video. In: ACM Transactions on Graphics. 2011 ; Vol. 30, No. 6.
@article{8a73c414778b4d358b7a4be4d9a6d272,
title = "Modeling and generating moving trees from video",
abstract = "We present a probabilistic approach for the automatic production of tree models with convincing 3D appearance and motion. The only input is a video of a moving tree that provides us an initial dynamic tree model, which is used to generate new individual trees of the same type. Our approach combines global and local constraints to construct a dynamic 3D tree model from a 2D skeleton. Our modeling takes into account factors such as the shape of branches, the overall shape of the tree, and physically plausible motion. Furthermore, we provide a generative model that creates multiple trees in 3D, given a single example model. This means that users no longer have to make each tree individually, or specify rules to make new trees. Results with different species are presented and compared to both reference input data and state of the art alternatives.",
author = "Chuan Li and Oliver Deussen and Yi-Zhe Song and Philip Willis and Peter Hall",
note = "Also published in SA '11 Proceedings of the 2011 SIGGRAPH Asia Conference Article No. 127 ACM New York, NY, USA {\circledC}2011 table of contents ISBN: 978-1-4503-0807-6 doi>10.1145/2024156.2024161",
year = "2011",
month = "12",
doi = "10.1145/2024156.2024161",
language = "English",
volume = "30",
journal = "ACM Transactions on Graphics",
issn = "0730-0301",
publisher = "Association for Computing Machinery",
number = "6",

}

TY - JOUR

T1 - Modeling and generating moving trees from video

AU - Li,Chuan

AU - Deussen,Oliver

AU - Song,Yi-Zhe

AU - Willis,Philip

AU - Hall,Peter

N1 - Also published in SA '11 Proceedings of the 2011 SIGGRAPH Asia Conference Article No. 127 ACM New York, NY, USA ©2011 table of contents ISBN: 978-1-4503-0807-6 doi>10.1145/2024156.2024161

PY - 2011/12

Y1 - 2011/12

N2 - We present a probabilistic approach for the automatic production of tree models with convincing 3D appearance and motion. The only input is a video of a moving tree that provides us an initial dynamic tree model, which is used to generate new individual trees of the same type. Our approach combines global and local constraints to construct a dynamic 3D tree model from a 2D skeleton. Our modeling takes into account factors such as the shape of branches, the overall shape of the tree, and physically plausible motion. Furthermore, we provide a generative model that creates multiple trees in 3D, given a single example model. This means that users no longer have to make each tree individually, or specify rules to make new trees. Results with different species are presented and compared to both reference input data and state of the art alternatives.

AB - We present a probabilistic approach for the automatic production of tree models with convincing 3D appearance and motion. The only input is a video of a moving tree that provides us an initial dynamic tree model, which is used to generate new individual trees of the same type. Our approach combines global and local constraints to construct a dynamic 3D tree model from a 2D skeleton. Our modeling takes into account factors such as the shape of branches, the overall shape of the tree, and physically plausible motion. Furthermore, we provide a generative model that creates multiple trees in 3D, given a single example model. This means that users no longer have to make each tree individually, or specify rules to make new trees. Results with different species are presented and compared to both reference input data and state of the art alternatives.

UR - http://www.scopus.com/inward/record.url?scp=82455188224&partnerID=8YFLogxK

UR - http://dl.acm.org/citation.cfm?id=2024161

U2 - 10.1145/2024156.2024161

DO - 10.1145/2024156.2024161

M3 - Article

VL - 30

JO - ACM Transactions on Graphics

T2 - ACM Transactions on Graphics

JF - ACM Transactions on Graphics

SN - 0730-0301

IS - 6

M1 - 127

ER -