AI Paper Atlas

Research map / 3D vision / Human pose estimation

Ego-Pose Estimation and Forecasting As Real-Time PD Control

Ye Yuan, Kris Kitani

ICCV 2019 · 3D vision › Human pose estimation · approach: Human motion prediction · 128 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 full reward (r_e, r_p, r_v terms) over pose-only reward r_q (ablation)ego-pose estimation policy · Cross-subject MoCapE_pose: 1.236 -> 1.183Improved
add end-effector reward to pose reward only (ablation)ego-pose estimation policy · Cross-subject MoCapnumber of resets: 14 -> 4Improved
add root rewards on top of r_q + r_e (ablation)ego-pose estimation policy · Cross-subject MoCapnumber of resets: 55 -> 4Improved
use proposed local-frame reward instead of DeepMimic reward (ablation)ego-pose estimation policy · Cross-subject MoCapE_pose: 1.515 -> 1.183Improved
use proposed local-frame reward instead of DeepMimic reward (ablation)ego-pose estimation policy · Cross-subject MoCapaverage acceleration: 17.504 -> 5.260Improved
add fail-safe reset mechanism (ablation)ego-pose estimation policy · Cross-subject MoCapE_pose: 1.206 -> 1.183Improved
add fail-safe reset mechanism (ablation)ego-pose estimation policy · Cross-subject MoCapnumber of resets: 4 -> 4No clear effect
use control-based PD policy instead of direct kinematic regression (PoseReg)ego-pose estimation · Single subject MoCapE_pose: 0.833 -> 0.640Improved
use PD action space with target joint angles instead of joint torques (VGAIL)ego-pose estimation · Single subject MoCapnumber of resets: 94 -> 1.4Improved
use physics-based forecasting policy instead of acLSTMego-pose forecasting · Cross-subject MoCap (3s)E_pose: 1.511 -> 1.339Improved
use physics-based forecasting policy instead of ERDego-pose forecasting · Cross-subject MoCap (1s)E_pose: 1.374 -> 1.179Improved

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