AI Paper Atlas

Research map / 3D vision / Human pose estimation

PPR: Physically Plausible Reconstruction from Monocular Videos

Gengshan Yang, Shuo Yang, John Z. Zhang, Zachary Manchester, Deva Ramanan

ICCV 2023 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 23 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
replace BANMo control-point deformation with skeleton deformationBANMo · AMA sambaChamfer distance (cm): 11.8 -> 8.9Improved
same skeleton deformation swapBANMo · AMA bouncingChamfer distance (cm): 12.8 -> 14.1Hurt
add differentiable physics simulation on top of skeleton modelBANMo +skel · AMA sambaChamfer distance (cm): 8.9 -> 8.3Improved
use differentiable physics instead of ground-prior scale fitting (ablation)PPR · AMA sambacontact (%): 26.3 -> 67.4Improved
use coordinate descent alternating rendering and physics instead of one cycle (ablation)PPR · AMA sambaChamfer distance (cm): 46.0 -> 8.3Improved
coordinate descent vs one cycle on foot skate (ablation)PPR · AMA sambafoot skate (cm): 1.1 -> 1.2Mixed
use PD feedback control instead of open-loop control (ablation)PPR · AMA sambacontact (%): 53.6 -> 67.4Improved
optimize mass and PD gains instead of freezing (ablation)PPR · AMA sambacontact (%): 50.4 -> 67.4Improved
PPR vs HuMoR on foot skatePPR · AMA bouncingfoot skate (cm): 2.6 -> 7.4Hurt

Earlier methods this paper compares with

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