A simple yet effective baseline for 3d human pose estimation

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions... (read more)

PDF Abstract ICCV 2017 PDF ICCV 2017 Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Human Pose Estimation Geometric Pose Affordance SIM-G-F MPJPE (CS) 67.3 # 1
MPJPE (CA) 57.8 # 1
PCK3D (CS) 93.9 # 1
PCK3D (CA) 95.5 # 1
3D Human Pose Estimation Geometric Pose Affordance SIM-P-F MPJPE (CS) 91.0 # 2
MPJPE (CA) 81.1 # 2
PCK3D (CS) 85.7 # 2
PCK3D (CA) 88.1 # 2
Monocular 3D Human Pose Estimation Human3.6M Martinez et. al. Average MPJPE (mm) 62.9 # 16
Use Video Sequence No # 1
Frames Needed 1 # 1
Need Ground Truth 2D Pose No # 1
3D Human Pose Estimation Human3.6M Multi-View Martinez Average MPJPE (mm) 87.3 # 50
Multi-View or Monocular Multi-View # 1
3D Human Pose Estimation HumanEva-I SH detections (SA) Mean Reconstruction Error (mm) 24.6 # 7

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