Research map / Video / Video generation
RapVerse: Coherent Vocals and Whole-Body Motion Generation from Text
Jiaben Chen, Xin Yan, Yihang Chen, Siyuan Cen, Zixin Wang, Qinwei Ma, Haoyu Zhen, Kaizhi Qian, Lie Lu, Chuang Gan
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 |
|---|---|---|---|
| train a tailored multimodal transformer instead of a pretrained LLM (ablation) | RapVerse model · RapVerse motion generation | FID: 48.25 -> 17.58 | Improved |
| train a tailored multimodal transformer instead of a pretrained LLM (ablation) | RapVerse model · RapVerse motion generation | LVD: 12.15 -> 7.23 | Improved |
| add separate compositional VQ-VAEs for face, body and hand (ablation) | RapVerse model · RapVerse motion generation | LVD: 10.12 -> 7.23 | Improved |
| add separate compositional VQ-VAEs for face, body and hand (ablation) | RapVerse model · RapVerse motion generation | FID: 19.15 -> 17.58 | Improved |
| add separate compositional VQ-VAEs for face, body and hand (ablation) | RapVerse model · RapVerse motion generation | DIV: 12.75 -> 14.08 | Improved |
| generate vocal and motion jointly instead of a cascaded DiffSinger + Talkshow pipeline | RapVerse model · RapVerse motion generation | FID: 23.42 -> 17.58 | Improved |
| generate vocal and motion jointly instead of a cascaded DiffSinger + Talkshow pipeline | RapVerse model · RapVerse motion generation | LVD: 9.38 -> 7.23 | Improved |
| unified joint model instead of dedicated vocal-only DiffSinger | RapVerse model · RapVerse vocal generation | MOS: 3.72 ± 0.12 -> 3.64 ± 0.15 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MotionCraft — MotionCraft: Physics-Based Zero-Shot Video Generation (NeurIPS 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation (ICML 2025 · similarity 0.87)
- Let's Chorus: Partner-aware Hybrid Song-Driven 3D Head Animation (CVPR 2025 · similarity 0.87)
- UniMuMo: Unified Text, Music, and Motion Generation (AAAI 2025 · similarity 0.86)
- Drop the Beat! Freestyler for Accompaniment Conditioned Rapping Voice Generation (AAAI 2025 · similarity 0.86)
- MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence (NeurIPS 2024 · similarity 0.85)
- GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks (NeurIPS 2024 · similarity 0.85)
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.
