AI Paper Atlas

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

ICCV 2025 · Video › Video generation · approach: Video-to-audio synthesis · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
train a tailored multimodal transformer instead of a pretrained LLM (ablation)RapVerse model · RapVerse motion generationFID: 48.25 -> 17.58Improved
train a tailored multimodal transformer instead of a pretrained LLM (ablation)RapVerse model · RapVerse motion generationLVD: 12.15 -> 7.23Improved
add separate compositional VQ-VAEs for face, body and hand (ablation)RapVerse model · RapVerse motion generationLVD: 10.12 -> 7.23Improved
add separate compositional VQ-VAEs for face, body and hand (ablation)RapVerse model · RapVerse motion generationFID: 19.15 -> 17.58Improved
add separate compositional VQ-VAEs for face, body and hand (ablation)RapVerse model · RapVerse motion generationDIV: 12.75 -> 14.08Improved
generate vocal and motion jointly instead of a cascaded DiffSinger + Talkshow pipelineRapVerse model · RapVerse motion generationFID: 23.42 -> 17.58Improved
generate vocal and motion jointly instead of a cascaded DiffSinger + Talkshow pipelineRapVerse model · RapVerse motion generationLVD: 9.38 -> 7.23Improved
unified joint model instead of dedicated vocal-only DiffSingerRapVerse model · RapVerse vocal generationMOS: 3.72 ± 0.12 -> 3.64 ± 0.15No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy