AI Paper Atlas

Research map / 3D vision / Human pose estimation

VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data

Jiajun Su, Chunyu Wang, Xiaoxuan Ma, Wenjun Zeng, Yizhou Wang

ECCV 2022 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 14 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 3D root estimator (REN 2D+3D) on top of 2D depth-map root estimation (ablation)VirtualPose · MuPoTS-3DMRPE_z (mm): 245.4 -> 165.0Improved
add 3D root estimator (REN 2D+3D) on top of 2D depth-map root estimation (ablation)VirtualPose · CMU PanopticMRPE_z (mm): 104.1 -> 93.6Improved
add Pose Estimation Network to refine root joint (ablation)VirtualPose · MuPoTS-3DMRPE_z (mm): 165.0 -> 159.8Improved
add Pose Estimation Network to refine root joint (ablation)VirtualPose · CMU PanopticMRPE_z (mm): 93.6 -> 86.0Improved
add Pose Estimation Network to refine root joint (ablation)VirtualPose · CMU PanopticMRPE (mm): 115.7 -> 97.0Improved
add 3D root estimator (REN 2D+3D) (ablation)VirtualPose · CMU PanopticMRPE (mm): 113.9 -> 115.7Hurt
add depth-based feature projection instead of projecting heatmaps to all voxels (ablation)VirtualPose · MuPoTS-3DMRPE (mm): 253.2 -> 204.0Improved
add depth-based feature projection instead of projecting heatmaps to all voxels (ablation)VirtualPose · MuPoTS-3DMRPE_z (mm): 210.5 -> 159.8Improved
train on virtual data from uniformly random cameras instead of a single camera (ablation)VirtualPose · CMU Panoptic cross-view test camera 14MRPE_z (mm): 454.6 -> 273.8Improved
generate training data from the known test camera 19 viewpoint (ablation)VirtualPose · CMU Panoptic camera 19MRPE_z (mm): 155.2 -> 62.3Improved
train with poses taken from MuPoTS-3D test set (ablation)VirtualPose · MuPoTS-3DPCK_abs: 44.0 -> 50.4Improved
add augmented backgrounds to training data (ablation)BDR baseline · MuCo-3DHP augmented-background testMRPE_z (mm): 267.8 -> 148.9Improved

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