AI Paper Atlas

Research map / Video / Video generation

DrawMotion: Generating 3D Human Motions by Freehand Drawing

Tao Wang, Lei Jin, Zhihua Wu, Qiang He, Jiaming Chu, Yu Cheng, Junliang Xing, Jian Zhao, Shuicheng Yan, Li Wang

TPAMI 2026 · Video › Video generation · approach: Text-to-motion diffusion · 0 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 Mahalanobis-distance clipping (threshold 1) to IFG (ablation)IFG · KIT-MLTraj.err.: 0.126 -> 0.069Improved
add Mahalanobis clipping to IFG (FID) (ablation)IFG · KIT-MLFID: 0.185 -> 0.141Improved
use deeper MCM layer for guidance (layer 1 to 3) (ablation)IFG · KIT-MLTraj.err.: 0.112 -> 0.099Improved
use deeper MCM layer for guidance (layer 1 to 3) (ablation)IFG · KIT-MLFID: 0.131 -> 0.146Hurt
increase IFG repeat from 10 to 100 (lr 50) (ablation)IFG · KIT-MLTraj.err.: 0.062 -> 0.026Improved
increase IFG repeat from 10 to 100 (time per batch) (ablation)IFG · KIT-MLTime/Batch (s): 7 -> 44Hurt
use efficient attention for text decoder instead of dot-product (ablation)DrawMotion · KIT-MLFID: 0.153 -> 0.135Improved
use efficient attention for draw decoder instead of dot-product (ablation)DrawMotion · KIT-MLTraj.Err.: 0.032 -> 0.113Hurt
add condition fusion and latent encoder to MCM versus mask baseline (ablation)MCM · KIT-MLFID: 0.151 -> 0.135Improved
add condition fusion alone (no latent encoder) (ablation)MCM · KIT-MLFID: 0.151 -> 0.187Hurt
bias reverse process toward drawing, p=80% instead of 20% (ablation)DrawMotion · KIT-MLStiSim: 52.2% -> 54.8%Improved
train/test with 3 stickmen rather than 0 (ablation)DrawMotion · KIT-MLStiSim: 42.65% -> 51.99%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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