Beat-It: Beat-Synchronized Multi-Condition 3D Dance Generation
Preprint
Abstract
Dance, as an art form, fundamentally hinges on the precise synchronization with musical beats. However, achieving aesthetically pleasing dance sequences from music is challenging, with existing methods often falling short in controllability and beat alignment. To address these shortcomings, this paper introduces Beat-It, a novel framework for beat-specific, key pose-guided dance generation. Unlike prior approaches, Beat-It uniquely integrates explicit beat awareness and key pose guidance, effectively resolving two main issues: the misalignment of generated dance motions with musical beats, and the inability to map key poses to specific beats, critical for practical choreography. Our approach disentangles beat conditions from music using a nearest beat distance representation and employs a hierarchical multi-condition fusion mechanism. This mechanism seamlessly integrates key poses, beats, and music features, mitigating condition conflicts and offering rich, multi-conditioned guidance for dance generation. Additionally, a specially designed beat alignment loss ensures the generated dance movements remain in sync with the designated beats. Extensive experiments confirm Beat-It's superiority over existing state-of-the-art methods in terms of beat alignment and motion controllability.Keywords
All Related Versions
This publication has 40 references indexed in Scilit:
- UDE: A Unified Driving Engine for Human Motion Generation2023
- Where is My Spot? Few-shot Image Generation via Latent Subspace Optimization2023
- Music-Driven Group Choreography2023
- EDGE: Editable Dance Generation From Music2023
- Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors2022
- Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory2022
- A Brand New Dance Partner: Music-Conditioned Pluralistic Dancing Controlled by Multiple Dance Genres2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audioComputers & Graphics, 2021
- On the Continuity of Rotation Representations in Neural Networks2019