{"ID":2826657,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.18181","arxiv_id":"2512.18181","title":"MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation","abstract":"With the rise of online dance-video platforms and rapid advances in AI-generated content (AIGC), music-driven dance generation has emerged as a compelling research direction. Despite substantial progress in related domains such as music-driven 3D dance generation, pose-driven image animation, and audio-driven talking-head synthesis, existing methods cannot be directly adapted to this task. Moreover, the limited studies in this area still struggle to jointly achieve high-quality visual appearance and realistic human motion. Accordingly, we present MACE-Dance, a music-driven dance video generation framework with cascaded Mixture-of-Experts (MoE). The Motion Expert performs music-to-3D motion generation while enforcing kinematic plausibility and artistic expressiveness, whereas the Appearance Expert carries out motion- and reference-conditioned video synthesis, preserving visual identity with spatiotemporal coherence. Specifically, the Motion Expert adopts a diffusion model with a BiMamba-Transformer hybrid architecture and a Guidance-Free Training (GFT) strategy, achieving state-of-the-art (SOTA) performance in 3D dance generation. The Appearance Expert employs a decoupled kinematic-aesthetic fine-tuning strategy, achieving state-of-the-art (SOTA) performance in pose-driven image animation. To better benchmark this task, we curate a large-scale and diverse dataset and design a motion-appearance evaluation protocol. Based on this protocol, MACE-Dance also achieves state-of-the-art performance. Code is available at https://github.com/AMAP-ML/MACE-Dance.","short_abstract":"With the rise of online dance-video platforms and rapid advances in AI-generated content (AIGC), music-driven dance generation has emerged as a compelling research direction. Despite substantial progress in related domains such as music-driven 3D dance generation, pose-driven image animation, and audio-driven talking-h...","url_abs":"https://arxiv.org/abs/2512.18181","url_pdf":"https://arxiv.org/pdf/2512.18181v3","authors":"[\"Kaixing Yang\",\"Jiashu Zhu\",\"Xulong Tang\",\"Ziqiao Peng\",\"Xiangyue Zhang\",\"Puwei Wang\",\"Jiahong Wu\",\"Xiangxiang Chu\",\"Hongyan Liu\",\"Jun He\"]","published":"2025-12-20T02:34:34Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false,"code_links":[{"ID":605759,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2826657,"paper_url":"https://arxiv.org/abs/2512.18181","paper_title":"MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation","repo_url":"https://github.com/AMAP-ML/MACE-Dance","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}