Research map / Video / Video generation
FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation
Ronghui Li, Junfan Zhao, Yachao Zhang, Mingyang Su, Zeping Ren, Han Zhang, Yansong Tang, Xiu Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use separate body and hand expert networks with a refine net (FDGN) instead of a single network (ablation) | FineNet · FineDance@Genre test | FID_h (hand): 1.20 -> 0.48 | Improved |
| add GCRM retrieval over generated candidates instead of concatenating fragments (ablation) | FDGN · FineDance@Genre test | Genre Matching Score (GS): 0.46 -> 0.74 | Improved |
| add GCRM retrieval over generated candidates (ablation) | FDGN · FineDance@Genre test | Diversity: 6.34 -> 5.99 | Hurt |
| generate long dances in 4s fragments with retrieval instead of directly generating the long sequence (ablation) | FDGN · FineDance@Genre test | FID: 2.85 -> 1.66 | Improved |
| plug GCRM into other generators (DeepDance, DanceRevolution) (ablation) | DeepDance · FineDance@Genre test | FID: 5.77 -> 4.91 | Improved |
| plug GCRM into DanceRevolution (ablation) | DanceRevolution · FineDance@Genre test | FID: 7.44 -> 6.99 | Improved |
| use FDGN as generator inside GCRM vs DeepDance/DanceRevolution (ablation) | FineNet · FineDance@Genre test | FID: 4.91 -> 1.66 | Improved |
| FineNet vs ChoreoMaster on diversity | FineNet · FineDance@Genre test | Diversity: 6.18 (ChoreoMaster) vs 5.99 (FineNet) | Hurt |
Closest papers by meaning
- OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data (CVPR 2026 · similarity 0.90)
- Music-Aligned Holistic 3D Dance Generation via Hierarchical Motion Modeling (ICCV 2025 · similarity 0.90)
- MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation (NeurIPS 2025 · similarity 0.90)
- DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning (AAAI 2024 · similarity 0.89)
- Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives (CVPR 2024 · similarity 0.88)
- DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
