Interactive motion generation from examples

Research output: Contribution to journalConference article

Abstract

There are many applications that demand large quantities of natural looking motion. It is difficult to synthesize motion that looks natural, particularly when it is people who must move. In this paper, we present a framework that generates human motions by cutting and pasting motion capture data. Selecting a collection of clips that yields an acceptable motion is a combinatorial problem that we manage as a randomized search of a hierarchy of graphs. This approach can generate motion sequences that satisfy a variety of constraints automatically. The motions are smooth and human-looking. They are generated in real time so that we can author complex motions interactively. The algorithm generates multiple motions that satisfy a given set of constraints, allowing a variety of choices for the animator. It can easily synthesize multiple motions that interact with each other using constraints. This framework allows the extensive re-use of motion capture data for new purposes.

Original languageEnglish (US)
Pages (from-to)483-490
Number of pages8
JournalACM Transactions on Graphics
Volume21
Issue number3
DOIs
StatePublished - Jan 1 2002
Externally publishedYes
EventACM Transactions on Graphics; Proceedings of ACM SIGGRAPH 2002 - , United States
Duration: Jul 23 2002Jul 26 2002

Fingerprint

Data acquisition

Keywords

  • Animation with constraints
  • Clustering
  • Graph search
  • Human motion
  • Motion capture
  • Motion synthesis

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design

Cite this

Interactive motion generation from examples. / Arikan, Okan; Forsyth, David Alexander.

In: ACM Transactions on Graphics, Vol. 21, No. 3, 01.01.2002, p. 483-490.

Research output: Contribution to journalConference article

@article{0c9a0a727a8a46749c3fabee56065fbe,
title = "Interactive motion generation from examples",
abstract = "There are many applications that demand large quantities of natural looking motion. It is difficult to synthesize motion that looks natural, particularly when it is people who must move. In this paper, we present a framework that generates human motions by cutting and pasting motion capture data. Selecting a collection of clips that yields an acceptable motion is a combinatorial problem that we manage as a randomized search of a hierarchy of graphs. This approach can generate motion sequences that satisfy a variety of constraints automatically. The motions are smooth and human-looking. They are generated in real time so that we can author complex motions interactively. The algorithm generates multiple motions that satisfy a given set of constraints, allowing a variety of choices for the animator. It can easily synthesize multiple motions that interact with each other using constraints. This framework allows the extensive re-use of motion capture data for new purposes.",
keywords = "Animation with constraints, Clustering, Graph search, Human motion, Motion capture, Motion synthesis",
author = "Okan Arikan and Forsyth, {David Alexander}",
year = "2002",
month = "1",
day = "1",
doi = "10.1145/566654.566606",
language = "English (US)",
volume = "21",
pages = "483--490",
journal = "ACM Transactions on Computer Systems",
issn = "0730-0301",
publisher = "Association for Computing Machinery (ACM)",
number = "3",

}

TY - JOUR

T1 - Interactive motion generation from examples

AU - Arikan, Okan

AU - Forsyth, David Alexander

PY - 2002/1/1

Y1 - 2002/1/1

N2 - There are many applications that demand large quantities of natural looking motion. It is difficult to synthesize motion that looks natural, particularly when it is people who must move. In this paper, we present a framework that generates human motions by cutting and pasting motion capture data. Selecting a collection of clips that yields an acceptable motion is a combinatorial problem that we manage as a randomized search of a hierarchy of graphs. This approach can generate motion sequences that satisfy a variety of constraints automatically. The motions are smooth and human-looking. They are generated in real time so that we can author complex motions interactively. The algorithm generates multiple motions that satisfy a given set of constraints, allowing a variety of choices for the animator. It can easily synthesize multiple motions that interact with each other using constraints. This framework allows the extensive re-use of motion capture data for new purposes.

AB - There are many applications that demand large quantities of natural looking motion. It is difficult to synthesize motion that looks natural, particularly when it is people who must move. In this paper, we present a framework that generates human motions by cutting and pasting motion capture data. Selecting a collection of clips that yields an acceptable motion is a combinatorial problem that we manage as a randomized search of a hierarchy of graphs. This approach can generate motion sequences that satisfy a variety of constraints automatically. The motions are smooth and human-looking. They are generated in real time so that we can author complex motions interactively. The algorithm generates multiple motions that satisfy a given set of constraints, allowing a variety of choices for the animator. It can easily synthesize multiple motions that interact with each other using constraints. This framework allows the extensive re-use of motion capture data for new purposes.

KW - Animation with constraints

KW - Clustering

KW - Graph search

KW - Human motion

KW - Motion capture

KW - Motion synthesis

UR - http://www.scopus.com/inward/record.url?scp=0036992635&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036992635&partnerID=8YFLogxK

U2 - 10.1145/566654.566606

DO - 10.1145/566654.566606

M3 - Conference article

AN - SCOPUS:0036992635

VL - 21

SP - 483

EP - 490

JO - ACM Transactions on Computer Systems

JF - ACM Transactions on Computer Systems

SN - 0730-0301

IS - 3

ER -