AI Paper Atlas

Research map / Video / Video generation

FreeMotion: MoCap-Free Human Motion Synthesis with Multimodal Large Language Models

Zhikai Zhang, Yitang Li, Haofeng Huang, Mingxian Lin, Li Yi

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 10 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
use GPT-4V keyframes plus physics tracking instead of data-driven MDM/MLDFreeMotion · HumanAct12user preference average: 30.83% -> 46.50%Improved
FreeMotion vs data-driven baselines on individual HumanAct12 actionsFreeMotion · HumanAct12user preference: Sit 26.00% vs MLD 44.00%; Walk 68.00% vs 22.00%Mixed
MLLM keyframes vs CLIP-based zero-shot methods on style transferFreeMotion · Style transferuser preference average: 22.25% -> 58.67%Improved
MLLM keyframes vs MotionCLIP/AvatarCLIP on Olympic sportsFreeMotion · Olympic sportsuser preferenceImproved
add detailed body-part descriptions in keyframe designer (ablation)FreeMotion · HumanAct12user preference: 26.00% -> 74.00%Improved
add visual feedback loop in keyframe animator (ablation)FreeMotion · HumanAct12user preference: 32.00% -> 68.00%Improved
MLLM-driven lying down on beds with rich contactFreeMotion · Human-scene interaction: Lie Downsuccess rate (%): 81.5 (UniHSI) -> 60Hurt
FreeMotion vs ALLSTEPS on stepping stonesFreeMotion · Stepping stonesmax step distanceMixed

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