Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909198292353024 |
|---|---|
| author | Aristidou, Andreas Yiannakidis, Anastasios Aberman, Kfir Cohen-Or, Daniel Shamir, Ariel Chrysanthou, Yiorgos |
| author_facet | Aristidou, Andreas Yiannakidis, Anastasios Aberman, Kfir Cohen-Or, Daniel Shamir, Ariel Chrysanthou, Yiorgos |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2111_12159 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure Aristidou, Andreas Yiannakidis, Anastasios Aberman, Kfir Cohen-Or, Daniel Shamir, Ariel Chrysanthou, Yiorgos Graphics Machine Learning I.3.7; I.2 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. |
| title | Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure |
| topic | Graphics Machine Learning I.3.7; I.2 |
| url | https://arxiv.org/abs/2111.12159 |