3D Human Pose Estimation with 2D Marginal Heatmaps

5 Jun 2018Aiden NibaliZhen HeStuart MorganLuke Prendergast

Automatically determining three-dimensional human pose from monocular RGB image data is a challenging problem. The two-dimensional nature of the input results in intrinsic ambiguities which make inferring depth particularly difficult... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
3D Human Pose Estimation MPI-INF-3DHP MargiPose 3DPCK 87.6 # 4
3D Human Pose Estimation MPI-INF-3DHP MargiPose AUC 48.8 # 6
3D Human Pose Estimation MPI-INF-3DHP MargiPose MJPE 87.6 # 4
3D Human Pose Estimation MPI-INF-3DHP MargiPose (multi-crop) 3DPCK 88.3 # 3
3D Human Pose Estimation MPI-INF-3DHP MargiPose (multi-crop) AUC 49.6 # 5
3D Human Pose Estimation MPI-INF-3DHP MargiPose (multi-crop) MJPE 85.2 # 3
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA) 3DPCK 94.8 # 2
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA) AUC 61.4 # 2
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA) MJPE 61.6 # 2
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA, multi-crop) 3DPCK 95.1 # 1
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA, multi-crop) AUC 62.2 # 1
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA, multi-crop) MJPE 60.1 # 1