AI Paper Atlas

Research map / 3D vision / Human pose estimation

Physics-Based Human Motion Estimation and Synthesis From Videos

Kevin Xie, Tingwu Wang, Umar Iqbal, Yunrong Guo, Sanja Fidler, Florian Shkurti

ICCV 2021 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 100 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 physics loss to kinematic optimization (ablation)pose optimization · Human3.6M (S9, S11)MPJPE (mm): 73.6 -> 68.1Improved
add physics loss to kinematic optimization (ablation)pose optimization · Human3.6M (S9, S11)global root position error (mm): 148.2 -> 85.1Improved
add physics loss to kinematic optimization (ablation)pose optimization · Human3.6M (S9, S11)e_smooth: 5.42 -> 4.0Improved
add physics loss to kinematic optimization (ablation)pose optimization · Human3.6M (S9, S11)sigma_smooth: 1.06 -> 1.3Hurt
add physics loss to kinematic optimization (ablation)pose optimization · Human3.6M (S9, S11)foot tangential velocity error: 4.65 -> 2.71Improved
add physics loss to kinematic optimization (ablation)pose optimization · Human3.6M (S9, S11)foot global height error: 95.7 -> 18.9Improved
train DLow on physics-corrected rather than kinematic pose estimates (ablation)DLow · Human3.6M S9/S11 motion synthesisADE (m): 0.590 -> 0.573Improved
train DLow on physics-corrected rather than kinematic pose estimates (ablation)DLow · Human3.6M S9/S11 motion synthesisFDE (m): 0.698 -> 0.685Improved
train DLow on physics-corrected rather than kinematic pose estimates (ablation)DLow · Human3.6M S9/S11 motion synthesisdiversity (APD): 10.53 -> 10.96Improved
train cVAE on physics-corrected rather than kinematic pose estimates (ablation)cVAE · Human3.6M S9/S11 motion synthesisADE (m): 0.639 -> 0.612Improved
train cVAE on physics-corrected rather than kinematic pose estimates (ablation)cVAE · Human3.6M S9/S11 motion synthesisdiversity (APD): 7.419 -> 7.413No clear effect
add physics loss to kinematic optimization (ablation)pose optimization · HumanEva walking (15 clips)body global position error (mm): 190.1 -> 101.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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