AI Paper Atlas

Research map / Video / Video generation

X-Dancer: Expressive Music to Human Dance Video Generation

Zeyuan Chen, Hongyi Xu, Guoxian Song, You Xie, Chenxu Zhang, Xin Chen, Chao Wang, Di Chang, Linjie Luo

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 16 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 global music context (ablation)X-Dancer transformer · In-House motionFVD: 265.73 -> 238.22Improved
add global motion context (ablation)X-Dancer transformer · In-House motionFVD: 247.54 -> 238.22Improved
add global music context (ablation)X-Dancer transformer · In-House motionBAS: 0.2142 -> 0.2182Improved
scale data from 10k to full 76k videos and model from GPT-medium (ablation)X-Dancer transformer · In-House motionFVD: 402.63 -> 238.22Improved
scale model from GPT-small (117M) to GPT-medium (345M) on 10k subset (ablation)X-Dancer transformer · In-House motionFVD: 332.93 -> 402.63Hurt
use multi-part instead of single-part VQ-VAE tokenization (ablation)X-Dancer pose tokenizer · Pose reconstructionPose L1 full body: 0.83 -> 0.50Improved
use multi-part instead of single-part VQ-VAE tokenization (ablation)X-Dancer video synthesis · Self-driven videoPSNR: 17.079 -> 19.148Improved
use motion token decoder instead of pose guider (ablation)X-Dancer video synthesis · In-House video synthesisFVD: 735.05 -> 507.06Improved
use motion token decoder instead of pose guider (ablation)X-Dancer video synthesis · In-House video synthesisID-SIM: 0.4894 -> 0.5317Improved
use motion token decoder instead of pose guider (ablation)Multi-part VQ-VAE · Self-driven videoFVD: 384.16 -> 295.87Improved
train motion transformer on AIST instead of in-house data (ablation)X-Dancer · In-House video synthesisFVD: 507.06 -> 549.38Hurt

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