AI Paper Atlas

Research map / Video / Video generation

MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm

Ziyan Guo, Zeyu Hu, De Wen Soh, Na Zhao

ICCV 2025 · Video › Video generation · approach: Text-to-motion diffusion · 23 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 motion curriculum learning (easy-to-hard task order with masked pre-training) (ablation)MotionLab · HumanML3D text generationFID: 1.956 -> 0.167Improved
add Aligned ROPE (1D) instead of 1D learnable encoding (ablation)MotionLab · HumanML3D trajectory generationAverage Error: 0.0886 -> 0.0334Improved
use MotionFlow Transformer instead of regular cross-attention transformer (ablation)MotionLab · HumanML3D text generationFID: 0.483 -> 0.167Improved
use rectified flows instead of diffusion (ablation)MotionLab · HumanML3D text generationFID: 0.301 -> 0.167Improved
add Task Instruction Modulation with CLIP text instructions (ablation)MotionLab · HumanML3D text generationFID: 0.223 -> 0.167Improved
train unified multi-task model instead of per-task specialists (ablation)MotionLab · MotionFix text-based editingR@1: 41.44 -> 56.34Improved
use 1D Aligned ROPE instead of 3D ROPE (ablation)MotionLab · HumanML3D text generationFID: 0.241 -> 0.167Improved
add masked pre-training before supervised fine-tuning (ablation)MotionLab · HumanML3D text generationFID: 0.861 -> 0.167Improved
replace one-hot or learnable task tokens with text instructions (ablation)MotionLab · HumanML3D text generationFID: 0.187 -> 0.167Improved

Later papers that compared with this method

1 later accepted paper reports MotionLab as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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