AI Paper Atlas

Research map / Video / Video generation

MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model

Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, Ziwei Liu

TPAMI 2024 · Video › Video generation · approach: Text-to-motion diffusion · 896 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 pretrained CLIP text encoder (ablation)MotionDiffuse with efficient attention · KIT-MLR Precision Top-1: 0.136 -> 0.417Improved
add pretrained CLIP text encoder (ablation)MotionDiffuse without efficient attention · KIT-MLR Precision Top-1: 0.288 -> 0.357Improved
add efficient attention with CLIP (ablation)MotionDiffuse · KIT-MLR Precision Top-1: 0.357 -> 0.417Improved
add efficient attention without CLIP (ablation)MotionDiffuse · KIT-MLR Precision Top-1: 0.288 -> 0.136Hurt
raise latent dimension from 256 to 512 (ablation)8-layer MotionDiffuse · KIT-MLR Precision Top-1: 0.198 -> 0.417Improved
raise latent dimension from 128 to 256 (ablation)8-layer MotionDiffuse · KIT-MLR Precision Top-1: 0.025 -> 0.198Improved
increase layers from 4 to 8 (ablation)MotionDiffuse dim 512 · KIT-MLR Precision Top-1: 0.405 -> 0.417No clear effect
increase layers from 8 to 12 (ablation)MotionDiffuse dim 512 · KIT-MLR Precision Top-1: 0.417 -> 0.412No clear effect
increase layers from 4 to 8 (ablation)MotionDiffuse dim 256 · KIT-MLR Precision Top-1: 0.095 -> 0.198Improved
increase latent dimension from 128 to 512 (ablation)8-layer MotionDiffuse · HumanAct12FID: 0.22 -> 0.07Improved
increase layers from 4 to 8 (ablation)MotionDiffuse dim 512 · HumanAct12FID: 0.09 -> 0.07Improved
use MotionDiffuse over Guo et al.text-to-motion · HumanML3DFID: 1.067 -> 0.630Improved

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