Rhythm is a Dancer: Music-Driven Motion Synthesis With Global Structure

被引:26
作者
Aristidou, Andreas [1 ,2 ]
Yiannakidis, Anastasios [1 ,2 ]
Aberman, Kfir [3 ]
Cohen-Or, Daniel [3 ]
Shamir, Ariel [4 ]
Chrysanthou, Yiorgos [1 ,2 ]
机构
[1] Univ Cyprus, Dept Comp Sci, CY-1678 Nicosia, Cyprus
[2] CYENS Ctr Excellence, CY-1016 Nicosia, Cyprus
[3] Tel Aviv Univ, Dept Comp Sci, IL-6997801 Tel Aviv, Israel
[4] Reichman Univ, Interdisciplinary Ctr Herzliya, Dept Comp Sci, IL-4610101 Herzliyya, Israel
关键词
Animation; global structure consistency; motion motifs; music-driven; motion signatures; BEAT TRACKING; STYLE; PHYSICS;
D O I
10.1109/TVCG.2022.3163676
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Synthesizing human motion with a global structure, such as a choreography, is a challenging task. Existing methods tend to concentrate on local smooth pose transitions and neglect the global context or the theme of the motion. In this work, we present a music-driven motion synthesis framework that generates long-term sequences of human motions which are synchronized with the input beats, and jointly form a global structure that respects a specific dance genre. In addition, our framework enables generation of diverse motions that are controlled by the content of the music, and not only by the beat. Our music-driven dance synthesis framework is a hierarchical system that consists of three levels: pose, motif, and choreography. The pose level consists of an LSTM component that generates temporally coherent sequences of poses. The motif level guides sets of consecutive poses to form a movement that belongs to a specific distribution using a novel motion perceptual-loss. And the choreography level selects the order of the performed movements and drives the system to follow the global structure of a dance genre. Our results demonstrate the effectiveness of our music-driven framework to generate natural and consistent movements on various dance types, having control over the content of the synthesized motions, and respecting the overall structure of the dance.
引用
收藏
页码:3519 / 3534
页数:16
相关论文
共 92 条
[71]  
Schulz A., 2011, P ACM SIGGRAPH POST
[72]   Dancing-to-music character animation [J].
Shiratori, Takaaki ;
Nakazawa, Atsushi ;
Ikeuchi, Katsushi .
COMPUTER GRAPHICS FORUM, 2006, 25 (03) :449-458
[73]   Audio to Body Dynamics [J].
Shlizerman, Eli ;
Dery, Lucio ;
Schoen, Hayden ;
Kemelmacher-Shlizerman, Ira .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :7574-7583
[74]   Interaction Patches for Multi-Character Animation [J].
Shum, Hubert P. H. ;
Komura, Taku ;
Shiraishi, Masashi ;
Yamazaki, Shuntaro .
ACM TRANSACTIONS ON GRAPHICS, 2008, 27 (05)
[75]  
Simonyan K, 2015, Arxiv, DOI arXiv:1409.1556
[76]  
Soga A., 2016, P ACM SIGGRAPH POST
[77]   Local Motion Phases for Learning Multi-Contact Character Movements [J].
Starke, Sebastian ;
Zhao, Yiwei ;
Komura, Taku ;
Zaman, Kazi .
ACM TRANSACTIONS ON GRAPHICS, 2020, 39 (04)
[78]  
Suwajanakorn S, 2017, ACM T GRAPHIC, V36, DOI [10.1145/3263919, 10.1145/3072959.3073640]
[79]   Dance with Melody: An LSTM-autoencoder Approach to Music-oriented Dance Synthesis [J].
Tang, Taoran ;
Jia, Jia ;
Mao, Hanyang .
PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, :1598-1606
[80]   A Deep Learning Approach for Generalized Speech Animation [J].
Taylor, Sarah ;
Kim, Taehwan ;
Yue, Yisong ;
Mahler, Moshe ;
Krahe, James ;
Rodriguez, Anastasio Garcia ;
Hodgins, Jessica ;
Matthews, Iain .
ACM TRANSACTIONS ON GRAPHICS, 2017, 36 (04)