Research map / Video / Video generation
OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data
Kaixing Yang, Jiashu Zhu, Xulong Tang, Ziqiao Peng, Xiangyue Zhang, Chubin Chen, Puwei Wang, Jiahong Wu, Xiangxiang Chu, Hongyan Liu, Jun He
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 |
|---|---|---|---|
| add music-text progressive specialization (MTPS) (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | MS: 93.74 -> 99.22 | Improved |
| add music-text progressive specialization (MTPS) (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | BAS: 0.257 -> 0.287 | Improved |
| add music-text progressive specialization (MTPS) (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | OC: 12.53 -> 13.08 | Improved |
| use progressive (weak shallow, strong deep) rather than reversed audio schedule (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | BAS: 0.234 -> 0.287 | Improved |
| use MERT instead of Wav2Vec2.0 as audio encoder (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | BAS: 0.241 -> 0.287 | Improved |
| use MERT instead of Wav2Vec2.0 as audio encoder (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | AQ: 56.10 -> 55.76 | Hurt |
| add Stage I text-adaptation warm-up (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | AQ: 52.92 -> 55.76 | Improved |
| add Stage I text-adaptation warm-up (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | BAS: 0.239 -> 0.287 | Improved |
| add Stage II anchored music integration (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | AQ: 51.38 -> 55.76 | Improved |
| add Stage II anchored music integration (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | BAS: 0.293 -> 0.287 | Hurt |
| add modality-specialized CFG (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | MS: 96.84 -> 99.22 | Improved |
| add modality-specialized CFG (ablation) | OmniDance · CIPE-Dance (MTI2V ablation) | BAS: 0.279 -> 0.287 | Improved |
Closest papers by meaning
- OpenDance: Multimodal Controllable 3D Dance Generation with Large-scale Internet Data (CVPR 2026 · similarity 0.94)
- DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions (ICCV 2025 · similarity 0.92)
- MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation (NeurIPS 2025 · similarity 0.91)
- DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning (AAAI 2024 · similarity 0.90)
- Bidirectional Autoregessive Diffusion Model for Dance Generation (CVPR 2024 · similarity 0.89)
- DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance (CVPR 2024 · similarity 0.89)
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.
