3D human pose estimation in video with temporal convolutions and semi-supervised training

CVPR 2019 Dario PavlloChristoph FeichtenhoferDavid GrangierMichael Auli

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
3D Human Pose Estimation Human3.6M Temporal convolution + semi-supervision Average MPJPE (mm) 46.8 # 7