FFD: Fine-Finger Diffusion Model for Music to Fine-grained Finger Dance Generation

Finger dance is an emerging social media trend using finger gesture motions for expression. Music to finger dance generation is challenging due to its fine-grained movements. Existing music-driven methods often fail to model subtle finger motions, yielding poor performances. We propose Fine-Finger Diffusion (FFD), the first end-to-end framework for music to finger dance generation. Our method employs a diffusion model to create rhythmically aligned finger movements while ensuring motion stability. A novel detail-aware loss (DAL) enhances temporal coherence by constraining inter-frame motion fluctuations. We introduce DanceFingers-4K, the first large-scale finger dance dataset containing 4007 video clips with music-motion pairs. Comprehensive evaluations demonstrate FFD’s superiority over existing approaches across objective metrics and user study.

• Publication year

  2025

• Venue

  Interspeech

• Publication date

  2025-08-17

• Fields of study

  Computer Science

• Identifiers
  DOI 10.21437/interspeech.2025-1105
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling

  2023cited by this paper
• EnchantDance: Unveiling the Potential of Music-Driven Dance Movement

  2023cited by this paper
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

  2023cited by this paper
• SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

  2023cited by this paper
• MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training

  2023cited by this paper
• FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing

  2023cited by this paper
• Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory

  2022influential reference
• FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation

  2022influential reference
• EDGE: Editable Dance Generation From Music

  2022influential reference
• A bi-directional attention guided cross-modal network for music based dance generation

  2022cited by this paper
• DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer

  2021cited by this paper
• AI Choreographer: Music Conditioned 3D Dance Generation with AIST++

  2021cited by this paper
• Learning to Generate Diverse Dance Motions with Transformer

  2020cited by this paper
• Music2Dance: Music-driven Dance Generation using WaveNet

  2020cited by this paper
• DeepDance: Music-to-Dance Motion Choreography With Adversarial Learning

  2020cited by this paper
• Denoising Diffusion Probabilistic Models

  2020cited by this paper
• Monocular Expressive Body Regression through Body-Driven Attention

  2020cited by this paper
• QuaterNet: A Quaternion-based Recurrent Model for Human Motion

  2018cited by this paper
• Dance with Melody: An LSTM-autoencoder Approach to Music-oriented Dance Synthesis

  2018cited by this paper
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

  2017cited by this paper
• GrooveNet : Real-Time Music-Driven Dance Movement Generation using Artificial Neural Networks

  2017cited by this paper
• A Deep Learning Framework for Character Motion Synthesis and Editing

  2016cited by this paper
• Music similarity-based approach to generating dance motion sequence

  2013cited by this paper
• Expressing technological metaphors in dance using structural illusion from embodied motion

  2013cited by this paper
• Dance illusioning the cyborg: technological themes in the movement practices and audience perception of three urban dance styles

  2012cited by this paper
• Learn2Dance: Learning Statistical Music-to-Dance Mappings for Choreography Synthesis

  2012cited by this paper
• Example-Based Automatic Music-Driven Conventional Dance Motion Synthesis

  2012cited by this paper
• Efficient content-based retrieval of motion capture data

  2005cited by this paper

• No citing papers are available for this paper.