Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model

• URL: http://arxiv.org/abs/2603.08023v1
• Date: Mon, 09 Mar 2026 06:59:03 GMT
• Title: Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
• Abstract summary: We propose emphMambaDance, a new dance generation approach that leverages a Mamba-based diffusion model.<n>Mamba, well-suited to handling long and autoregressive sequences, is integrated into our two-stage diffusion architecture, substituting off-the-shelf Transformer.<n>We show that our proposed method effectively generates plausible dance movements while reflecting essential characteristics, consistently from short to long dances, compared to the previous methods.
• Score: 8.542693293312935
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dance is a form of human motion characterized by emotional expression and communication, playing a role in various fields such as music, virtual reality, and content creation. Existing methods for dance generation often fail to adequately capture the inherently sequential, rhythmical, and music-synchronized characteristics of dance. In this paper, we propose \emph{MambaDance}, a new dance generation approach that leverages a Mamba-based diffusion model. Mamba, well-suited to handling long and autoregressive sequences, is integrated into our two-stage diffusion architecture, substituting off-the-shelf Transformer. Additionally, considering the critical role of musical beats in dance choreography, we propose a Gaussian-based beat representation to explicitly guide the decoding of dance sequences. Experiments on AIST++ and FineDance datasets for each sequence length show that our proposed method effectively generates plausible dance movements while reflecting essential characteristics, consistently from short to long dances, compared to the previous methods. Additional qualitative results and demo videos are available at \small{https://vision3d-lab.github.io/mambadance}.

Related papers

• DanceChat: Large Language Model-Guided Music-to-Dance Generation [8.455652926559427]
  Music-to-dance generation aims to synthesize human dance motion conditioned on musical input.<n>We introduce DanceChat, a Large Language Model (LLM)-guided music-to-dance generation approach.
  arXiv  Detail & Related papers  (2025-06-12T11:03:47Z)
• Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation [22.729568599120846]
  We propose Danceba, a novel framework that leverages gating mechanism to enhance rhythm-aware feature representation.<n>Phase-Based Rhythm Extraction (PRE) to precisely extract rhythmic information from musical phase data.<n>Temporal-Gated Causal Attention (TGCA) to focus on global rhythmic features.<n> Parallel Mamba Motion Modeling (PMMM) architecture to separately model upper and lower body motions.
  arXiv  Detail & Related papers  (2025-03-21T17:42:50Z)
• Controllable Dance Generation with Style-Guided Motion Diffusion [49.35282418951445]
  Dance plays an important role as an artistic form and expression in human culture, yet the creation of dance remains a challenging task.<n>Most dance generation methods rely solely on music, seldom taking into consideration intrinsic attributes such as music style or genre.<n>In this work, we introduce Flexible Dance Generation with Style Description Prompts (DGSDP), a diffusion-based framework suitable for diversified tasks of dance generation.
  arXiv  Detail & Related papers  (2024-06-12T04:55:14Z)
• Bidirectional Autoregressive Diffusion Model for Dance Generation [26.449135437337034]
  We propose a Bidirectional Autoregressive Diffusion Model (BADM) for music-to-dance generation. A bidirectional encoder is built to enforce that the generated dance is harmonious in both the forward and backward directions. To make the generated dance motion smoother, a local information decoder is built for local motion enhancement.
  arXiv  Detail & Related papers  (2024-02-06T19:42:18Z)
• DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation [89.50310360658791]
  We present a novel cascaded motion diffusion model, DiffDance, designed for high-resolution, long-form dance generation. This model comprises a music-to-dance diffusion model and a sequence super-resolution diffusion model. We demonstrate that DiffDance is capable of generating realistic dance sequences that align effectively with the input music.
  arXiv  Detail & Related papers  (2023-08-05T16:18:57Z)
• FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation [33.9261932800456]
  FineDance is the largest music-dance paired dataset with the most dance genres. To address monotonous and unnatural hand movements existing in previous methods, we propose a full-body dance generation network. To further enhance the genre-matching and long-term stability of generated dances, we propose a Genre&Coherent aware Retrieval Module.
  arXiv  Detail & Related papers  (2022-12-07T16:10:08Z)
• Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory [92.81383016482813]
  We propose a novel music-to-dance framework, Bailando, for driving 3D characters to dance following a piece of music. We introduce an actor-critic Generative Pre-trained Transformer (GPT) that composes units to a fluent dance coherent to the music. Our proposed framework achieves state-of-the-art performance both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-03-24T13:06:43Z)
• Music-to-Dance Generation with Optimal Transport [48.92483627635586]
  We propose a Music-to-Dance with Optimal Transport Network (MDOT-Net) for learning to generate 3D dance choreographs from music. We introduce an optimal transport distance for evaluating the authenticity of the generated dance distribution and a Gromov-Wasserstein distance to measure the correspondence between the dance distribution and the input music.
  arXiv  Detail & Related papers  (2021-12-03T09:37:26Z)
• Learning to Generate Diverse Dance Motions with Transformer [67.43270523386185]
  We introduce a complete system for dance motion synthesis. A massive dance motion data set is created from YouTube videos. A novel two-stream motion transformer generative model can generate motion sequences with high flexibility.
  arXiv  Detail & Related papers  (2020-08-18T22:29:40Z)
• Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning [55.854205371307884]
  We formalize the music-conditioned dance generation as a sequence-to-sequence learning problem. We propose a novel curriculum learning strategy to alleviate error accumulation of autoregressive models in long motion sequence generation. Our approach significantly outperforms the existing state-of-the-arts on automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-06-11T00:08:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.