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
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Human Pose Estimation MPI-INF-3DHP MargiPose 3DPCK 87.6 # 7
AUC 48.8 # 9
MJPE 87.6 # 5
3D Human Pose Estimation MPI-INF-3DHP MargiPose (multi-crop) 3DPCK 88.3 # 5
AUC 49.6 # 8
MJPE 85.2 # 4
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA) 3DPCK 94.8 # 2
AUC 61.4 # 3
MJPE 61.6 # 2
3D Human Pose Estimation MPI-INF-3DHP MargiPose (Procrustes alignment, PA, multi-crop) 3DPCK 95.1 # 1
AUC 62.2 # 2
MJPE 60.1 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet