AI Paper Atlas

Research map / 3D vision / Human pose estimation

AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion

Hongjie Li, Heng Yu, Jiaman Li, Hong-Xing Yu, Ehsan Adeli, C. Karen Liu, Jiajun Wu

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
add hybrid data-source training (local reprojected poses from GVHMR) to AnyLift (ablation)AnyLift · Gymnastics Internet videosJ2D: 36.1 -> 21.6Improved
add hybrid data-source training (ablation)AnyLift · Gymnastics Internet videosFID: 11.2 -> 10.9Improved
add hybrid data-source training (ablation)AnyLift · Martial Arts Internet videosJ2D: 25.2 -> 15.1Improved
add hybrid data-source training (ablation)AnyLift · Martial Arts Internet videosFID: 4.3 -> 3.6Improved
human study: prefer full AnyLift over version without hybrid training (ablation)AnyLift · Human study (Internet videos)preference for ground contact / motion quality: 65.6% ground contact, 66.3% motion qualityImproved
camera-conditioned diffusion with hybrid training instead of MVLiftAnyLift vs MVLift · Gymnastics Internet videosJ2D: 33.1 -> 21.6Improved
AnyLift instead of MVLiftAnyLift vs MVLift · Martial Arts Internet videosJ2D: 24.6 -> 15.1Improved
AnyLift instead of MVLift under synthetic dynamic camerasAnyLift vs MVLift · AIST++ (dynamic camera)MPJPE: 122.1 -> 109.3Improved
AnyLift instead of MVLift under static camerasAnyLift vs MVLift · AIST++ (static camera)PA-MPJPE: 79.2 -> 82.3Hurt
AnyLift instead of MVLift under static camerasAnyLift vs MVLift · AIST++ (static camera)root translation error Troot: 67.6 -> 64.9Improved
AnyLift (trained on 2D only) instead of GVHMR (trained on AMASS 3D)AnyLift vs GVHMR · AIST++ (static camera)MPJPE: 97.6 -> 108.0Hurt
AnyLift instead of GVHMRAnyLift vs GVHMR · Gymnastics Internet videosfoot sliding FS: 0.061 -> 0.152Hurt

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