AI Paper Atlas

Research map / Video / Video generation

Beat-It: Beat-Synchronized Multi-Condition 3D Dance Generation

Zikai Huang, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Chenxi Zheng, Jing Qin, Shengfeng He

ECCV 2024 · Video › Video generation · approach: Video-to-audio synthesis · 15 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
add hierarchical multi-condition fusion instead of one-stage concatenation (ablation)Beat-It · AIST++PFC: 25.626 -> 0.966Improved
add hierarchical multi-condition fusion (ablation)Beat-It · AIST++BAP: 0.323 -> 0.793Improved
add beat-aware dilation instead of vanilla masked attention (ablation)Beat-It · AIST++BAP: 0.371 -> 0.793Improved
add beat-aware dilation instead of vanilla masked attention (ablation)Beat-It · AIST++KPD: 0.389 -> 0.306Improved
add beat alignment loss (ablation)Beat-It · AIST++BAS: 0.397 -> 0.661Improved
add beat alignment loss (ablation)Beat-It · AIST++BAP: 0.411 -> 0.793Improved
use Beat-It with beat condition and keyframes instead of EDGE keyframe blendingdance generation · AIST++BAS: 0.235 -> 0.661Improved
use Beat-It instead of EDGEdance generation · AIST++KPD: 0.859 -> 0.306Improved
use Beat-It instead of EDGEdance generation · AIST++Div_k: 9.743 -> 9.660No clear effect

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