[1911.02001] Dancing to Music

Dancing to music is an instinctive move by humans. Learning to model the music-to-dance generation process is, however, a challenging problem. It requires significant efforts to measure the correlation between music and dance as one needs to simultaneously consider multiple aspects, such as style and beat of both music and dance. Additionally, dance is inherently multimodal and various following movements of a pose at any moment are equally likely. In this paper, we propose a synthesis-by-analysis learning framework to generate dance from music. In the analysis phase, we decompose a dance into a series of basic dance units, through which the model learns how to move. In the synthesis phase, the model learns how to compose a dance by organizing multiple basic dancing movements seamlessly according to the input music. Experimental qualitative and quantitative results demonstrate that the proposed method can synthesize realistic, diverse,style-consistent, and beat-matching dances from mus

6 mentions: @hardmaru@roadrunning01@highqualitysh1t@yu4u@zuNaoya
Date: 2019/11/06 11:21

Referring Tweets

@hardmaru Dancing to Music This paper looks at generating dance from music through a decomposition to composition learning framework. #NeurIPS2019 Paper t.co/q4ojHXOw76 Project t.co/4Vxi8um9J6 t.co/NxvQuSVSfe
@highqualitysh1t NVIDIA NVLabs: Dancing2Music Paper: t.co/Vw2yee08cQ Video: t.co/kxelEsIRi6 Repo (no code yet): t.co/KNxgFXc38Z t.co/3u5xw99y7O
@roadrunning01 Dancing to Music pdf: t.co/ZNM0TYXY1M abs: t.co/L3WNQrSUXj github: t.co/xDo8qwRcj1 t.co/NJyYFjHs4a

Bookmark Comments