AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Ego-Pose Estimation via Imitation Learning

Ye Yuan, Kris Kitani

ECCV 2018 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 66 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 policy fine-tuning (20 iterations) on the test sequence, starting from estimated initial state (ablation)Ours (video-conditioned policy) · Virtual test set (20 trajectories)Pose error: 1.2219 -> 0.9779Improved
add policy fine-tuning (20 iterations) on the test sequence, starting from estimated initial state (ablation)Ours (video-conditioned policy) · Virtual test set (20 trajectories)Velocity error: 7.5337 -> 6.5143Improved
add policy fine-tuning (20 iterations) on the test sequence, starting from estimated initial state (ablation)Ours (video-conditioned policy) · Virtual test set (20 trajectories)Smoothness: 12.2472 -> 11.9876Improved
use ground-truth initial state instead of estimated initial state (ablation)Ours (video-conditioned policy) · Virtual test set (20 trajectories)Pose error: 0.9779 -> 0.6688Improved
use ground-truth initial state instead of estimated initial state (ablation)Ours (video-conditioned policy) · Virtual test set (20 trajectories)Velocity error: 6.5143 -> 6.0761Improved
use ground-truth initial state instead of estimated initial state (ablation)Ours (video-conditioned policy) · Virtual test set (20 trajectories)Smoothness: 11.9876 -> 12.2968No clear effect
physics-based control policy instead of direct pose regressionEgo-pose estimator · Virtual test set (20 trajectories)Smoothness: 36.1628 -> 11.9876Improved
physics-based control policy instead of direct pose regressionEgo-pose estimator · Virtual test set (20 trajectories)Pose error: 0.8310 -> 0.9779Hurt
physics-based control policy instead of Path poseEgo-pose estimator · Virtual test set (20 trajectories)Pose error: 1.7643 -> 0.9779Improved
physics-based control policy with fine-tuning instead of pose regression on real videosEgo-pose estimator · Real-world egocentric videos (12 sequences)2D projection error: 0.1621 -> 0.1325Improved
physics-based control policy with fine-tuning instead of pose regression on real videosEgo-pose estimator · Real-world egocentric videos (12 sequences)Smoothness: 44.11 -> 11.54Improved

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