Papers › AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
AI Choreographer: Music Conditioned 3D Dance Generation with AIST++
RuiLong Li, Shan Yang, David A. Ross, Angjoo Kanazawa
We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion conditioned on music. The proposed AIST++ dataset contains 5.2 hours of 3D dance motion in 1408 sequences, covering 10 dance genres with multi-view videos with known camera poses -- the largest dataset of this kind to our knowledge. We show that naively applying sequence models such as transformers to this dataset for the task of music conditioned 3D motion generation does not produce satisfactory 3D motion that is well correlated with the input music. We overcome these shortcomings by introducing key changes in its architecture design and supervision: FACT model involves a deep cross-modal transformer block with full-attention that is trained to predict N future motions. We empirically show that these changes are key factors in generating long sequences of realistic dance motion that are well-attuned to the input music. We conduct extensive experiments on AIST++ with user studies, where our method outperforms recent state-of-the-art methods both qualitatively and quantitatively.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Motion Synthesis | AIST++ | AI Choreographer | Beat alignment score | 0.221 | #6 of 12 | Archive leaderboard | report |
| Motion Synthesis | AIST++ | AI Choreographer | FID | 35.35 | #6 of 12 | Archive leaderboard | report |
| Motion Synthesis | BRACE | AIST++ | Beat DTW cost | 12.92 | #2 of 3 | Archive leaderboard | report |
| Motion Synthesis | BRACE | AIST++ | Beat alignment score | 0.136 | #2 of 3 | Archive leaderboard | report |
| Motion Synthesis | BRACE | AIST++ | Footwork average | 40.73 | #2 of 3 | Archive leaderboard | report |
| Motion Synthesis | BRACE | AIST++ | Frechet Inception Distance | 0.5743 | #2 of 3 | Archive leaderboard | report |
| Motion Synthesis | BRACE | AIST++ | Powermove average | 52.89 | #2 of 3 | Archive leaderboard | report |
| Motion Synthesis | BRACE | AIST++ | Toprock average | 6.39 | #2 of 3 | Archive leaderboard | report |
| Motion Synthesis | FineDance | FACT | BAS | 0.1831 | #8 of 8 | Archive leaderboard | report |
| Motion Synthesis | FineDance | FACT | fid_k | 113.38 | #8 of 8 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections