FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation
Authors:
Top Cited Papers
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10200-10209
Abstract
Generating full-body and multi-genre dance sequences from given music is a challenging task, due to the limitations of existing datasets and the inherent complexity of the fine-grained hand motion and dance genres. To address these problems, we propose FineDance, which contains 14.6 hours of music-dance paired data, with fine-grained hand motions, fine-grained genres (22 dance genres), and accurate posture. To the best of our knowledge, FineDance is the largest music-dance paired dataset with the most dance genres. Additionally, to address monotonous and unnatural hand movements existing in previous methods, we propose a full-body dance generation network, which utilizes the diverse generation capabilities of the diffusion model to solve monotonous problems, and use expert nets to solve unreal problems. To further enhance the genre-matching and long-term stability of generated dances, we propose a Genre&Coherent aware Retrieval Module. Besides, we propose a novel metric named Genre Matching Score to evaluate the genre-matching degree between dance and music. Quantitative and qualitative experiments demonstrate the quality of FineDance, and the state-of-the-art performance of FineNet. The FineDance Dataset and more qualitative samples can be found at website.Keywords
All Related Versions
Funding Information
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
This publication has 36 references indexed in Scilit:
- Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory2022
- We are More than Our Joints: Predicting how 3D Bodies Move2021
- Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audioComputers & Graphics, 2021
- Expressive Body Capture: 3D Hands, Face, and Body From a Single Image2019
- Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition2019
- Neural Kinematic Networks for Unsupervised Motion Retargetting2018
- Learning Human Motion Models for Long-Term Predictions2017
- An automatic system for humanoid dance creationBiologically Inspired Cognitive Architectures, 2016
- Music similarity-based approach to generating dance motion sequenceMultimedia Tools and Applications, 2012
- Motion Synthesis By Example1996