3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training

AAAI Conference on Artificial Intelligence, AAAI 2020 2020 Cheng YuBo YangBo WangRobby T. Tan

Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in the recent years. Generally, the performance of existing methods drops when the target person is too small/large, or the motion is too fast/slow relative to the scale and speed of the training data... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
3D Human Pose Estimation 3DPW Spatio-Temporal Network PA-MPJPE 71.8 # 5
3D Human Pose Estimation Human3.6M Spatio-Temporal Network Average MPJPE (mm) 40.1 # 8
Using 2D ground-truth joints No # 1
Multi-View or Monocular Monocular # 1
3D Human Pose Estimation HumanEva-I Spatio-Temporal Network Mean Reconstruction Error (mm) 13.5 # 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