AI Paper Atlas

Research map / 3D vision / 3D generation

MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations

Yuhua Luo, Junsheng Zhang, Mengyin Liu, Xincheng Lin, Ming Yan, Zhudi Chen, Chenglu Wen, Lan Xu, Siqi Shen, Cheng Wang

ICML 2026 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 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 Temporal Multi-scale Tokenization (ablation)MotionMAR · AMASS S1MPJPE: 3.41 -> 2.82Improved
add Motion Refinement Network (Bi-GRU) (ablation)MotionMAR · AMASS S1Jitter: 42.85 -> 5.17Improved
add Motion Refinement Network (Bi-GRU) (ablation)MotionMAR · AMASS S1MPJVE: 43.9 -> 16.23Improved
add Scale-aware Control module (ablation)MotionMAR · AMASS S1Root PE: 3.22 -> 2.58Improved
add Scale-aware Control module (ablation)MotionMAR · AMASS S1Hand PE: 1.21 -> 0.83Improved
add MRN (ablation)MotionMAR · AMASS S1Hand PE: 0.84 -> 0.83No clear effect
replace SAGE single-scale VQ with TMT (ablation)SAGE · AMASS S1reconstruction errorImproved
MotionMAR versus RPM on jitter in large-scale settingMotionMAR · AMASS S3Jitter: 3.67 (RPM) vs 4.14Hurt

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