AI Paper Atlas

Research map / 3D vision / Human pose estimation

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation

Xinshun Wang, Peiming Li, Ziyi Wang, Zhongbin Fang, Zhichao Deng, Songtao Wu, Jason Li, Mengyuan Liu

CVPR 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 1 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 vision-guided fused tokenizer (0.5/0.5) instead of skeleton-only (ablation)Superman · Human3.6M pose estimationN-MPJPE (mm): 47.8 -> 44.9Improved
use vision-guided fused tokenizer instead of visual-only (ablation)Superman · Human3.6M pose estimationN-MPJPE (mm): 51.3 -> 44.9Improved
use balanced commitment weights 0.5/0.5 instead of 0.7/0.3 (ablation)Superman tokenizer · Tokenizer reconstructionreconstruction error (mm): 5.3 -> 4.7Improved
train one unified model instead of specialized per-task models (ablation)Superman · Human3.6M pose estimationMPJPE (mm): 46.5 -> 44.9Improved
train one unified model instead of specialized per-task models (ablation)Superman · Human3.6M motion predictionMPJPE (mm): 27.3 -> 26.1Improved
train one unified model instead of specialized per-task models (ablation)Superman · Human3.6M motion in-betweeningMPJPE (mm): 33.1 -> 30.6Improved
scale MLLM from 3B to 7B (ablation)Superman · Human3.6M PE and MPMPJPE (mm)Improved
increase codebook capacity (e.g. 4096x1024 to 4096x2048) (ablation)Superman · Human3.6M PE and MPMPJPE (mm)Improved
add MAFT module (<0.2% extra params) for pose estimation (ablation)Superman · Human3.6M pose estimationN-MPJPE (mm): 44.90 -> 39.41Improved
Superman (no MAFT) vs Human-in-Context on pose estimationSuperman · Human3.6M pose estimationN-MPJPE (mm): 44.77 -> 44.90Mixed
zero-shot transfer from Human3.6M to 3DPWSuperman · 3DPW motion predictionMPJPE avg (mm): 140.71 -> 62.05Improved
zero-shot transfer from Human3.6M to 3DPWSuperman · 3DPW motion in-betweeningMPJPE avg (mm): 103.97 -> 60.68Improved

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