AI Paper Atlas

Research map / Video / Video generation

MotionCtrl: A Real-time Controllable Vision-Language-Motion Model

Bin Cao, Sipeng Zheng, Ye Wang, Lujie Xia, Qianshan Wei, Qin Jin, Jing Liu, Zongqing Lu

ICCV 2025 · Video › Video generation · approach: Text-to-motion diffusion · 2 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
replace VQ with part-aware residual quantization (PRQ)MotionCtrl · HumanML3D (text-to-motion)FID: 0.141 to 0.056Improved
share joints across body parts in PRQ (ablation)MotionCtrl PRQ4 · HuMo-I2PMFID: 2.471 to 1.831Improved
share joints across body parts in PRQ (ablation)PRQ4 tokenizer · HumanML3D reconstructionFID: 0.042 -> 0.007Improved
use part-level descriptions in training (ablation)MotionCtrl-PRQ4 · HuMo-I2PMFID: 4.281 -> 1.831Improved
use part-level descriptions in training (ablation)MotionCtrl-RQ6 · HuMo-I2PMFID: 4.025 -> 3.752No clear effect
increase PRQ quantization layers from 4 to 6 (ablation)MotionCtrl · HuMo-I2PMFID: 1.831 -> 2.357Hurt
increase PRQ quantization layers from 4 to 6 (ablation)PRQ tokenizer · HumanML3D reconstructionFID: 0.007 -> 0.004Improved
add vision-text-motion alignment stage (ablation)MotionCtrl · HuMo-T2MFID: 7.053 -> 5.791Improved
add MPI task to multi-task training (ablation)MotionCtrl · HuMo-T2MFID: 6.582 -> 6.052Improved
add I2PM and I2LM tasks to multi-task training (ablation)MotionCtrl · HuMo-T2MFID: 6.052 -> 5.791Improved
add I2M task to T2M training (ablation)MotionCtrl · HuMo-T2MFID: 7.152 -> 6.582Improved
scale training data from HumanML3D to HuMo100MMotionCtrl · HuMo-unseen I2UFID: 65.04 -> 8.65Improved

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