Example-based synthesis of rhythmic motions guided by sound signals = 소리 신호의 유도에 따른 예제 기반 율동 합성

Real-time animation of human-like characters is an active research area in computer graphics. The conventional approaches have, however, hardly dealt with the rhythm and energy of motions, which are essential in handling and generating rhythmic motions of which the styles match those of background sound signals. In this thesis, we present a novel scheme for synthesizing a new rhythmic motion for an input sound signal from unlabelled example motions. Our scheme first captures the motion beats and variations of music energy from the example motions and their accompanying sound signals. We extract the basic movements and their transitions, and then train their music-energy observation probabilities. By using those data, our scheme then constructs a movement transition graph that represents the example motions. Given an input sound signal, our scheme finally synthesizes a novel motion in an on-line manner while traversing the motion transition graph, which is synchronized with the input sound signal and satisfies kinematic constraints given explicitly and implicitly. The resulting motion also has a proper style that matches that of the sound signal. Through experiments, we have demonstrated that our scheme can effectively produce a variety of rhythmic motions.
Advisors
Shin, Sung-Yongresearcher신성용researcher
Publisher
한국과학기술원
Issue Date
2004
Identifier
237674/325007 / 000995105
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전산학전공, 2004.2, [ ix, 87 p. ]

Keywords

MOTION BLENDING; MOTION TRANSITION; MOTION BEAT ANALYSIS; MOTION SYNTHESIS; MUSIC ANALYSIS; 음악 분석; 동작 블렌딩; 동작 전이; 동작 비트 분석; 동작 합성

URI
http://hdl.handle.net/10203/33202
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=237674&flag=t
Appears in Collection
CS-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.
  • Hit : 97
  • Download : 0
  • Cited 0 times in thomson ci

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0