AI Paper Atlas

Research map / 3D vision / Human pose estimation

Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video

Zongmian Li, Jiri Sedlar, Justin Carpentier, Ivan Laptev, Nicolas Mansard, Josef Sivic

CVPR 2019 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 70 citations (OpenAlex)

Check 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
Jointly estimate person and object trajectories with contact and dynamics constraints3D motion reconstruction · ParkourMPJPE (mm): 135.65 -> 122.11Improved
Jointly estimate person and object trajectories with contact and dynamics constraints3D motion reconstruction · HandtoolMPJPE (mm): 103.49 -> 102.38Improved
Use person-object interaction modeling to refine object endpoint locationsObject endpoint estimation · HandtoolEndpoint accuracy within 25/50/100 pixels (%): Mask R-CNN to Ours: Barbell 33/42/54 -> 38/71/98; Spade 54/79/93 -> 57/86/99; Hammer 35/44/45 -> 61/91/99; Scythe 63/72/Improved

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