PC-Dance: Posture-controllable Music-driven Dance Synthesis

Gao, Jibin; Pu, Junfu; Zhang, Honglun; Shan, Ying; Zheng, Wei-Shi

doi:10.1145/3503161.3548099

Cited by 3 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To tackle these issues, direct generation methods (Ahn et al 2020;Huang et al 2021Huang et al , 2022Zhuang et al 2022;Valle-Pérez et al 2021;Wang et al 2022;Gao et al 2022;Li et al 2022Li et al , 2020Tseng, Castellon, and Liu 2023) have been proposed which generate dance motion from scratch. These methods are trained in a supervised learning fashion, with music as the conditioning input and real human dance as the supervisory signal.…”

Section: Music-conditioned Dance Generationmentioning

confidence: 99%

Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations

Wang,

Zhuang,

et al. 2024

AAAI

View full text Add to dashboard Cite

This paper presents an Exploratory 3D Dance generation framework, E3D2, designed to address the exploration capability deficiency in existing music-conditioned 3D dance generation models. Current models often generate monotonous and simplistic dance sequences that misalign with human preferences because they lack exploration capabilities.The E3D2 framework involves a reward model trained from automatically-ranked dance demonstrations, which then guides the reinforcement learning process. This approach encourages the agent to explore and generate high quality and diverse dance movement sequences. The soundness of the reward model is both theoretically and experimentally validated. Empirical experiments demonstrate the effectiveness of E3D2 on the AIST++ dataset.

show abstract