Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

CVPR 2017  ·  Denis Tome, Chris Russell, Lourdes Agapito ·

We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks. We take an integrated approach that fuses probabilistic knowledge of 3D human pose with a multi-stage CNN architecture and uses the knowledge of plausible 3D landmark locations to refine the search for better 2D locations... The entire process is trained end-to-end, is extremely efficient and obtains state- of-the-art results on Human3.6M outperforming previous approaches both on 2D and 3D errors. read more

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
3D Human Pose Estimation Human3.6M Projected-pose belief maps + 2D fusion layers Average MPJPE (mm) 88.39 # 60
Weakly-supervised 3D Human Pose Estimation Human3.6M Tome et al. Average MPJPE (mm) 88.4 # 7
Number of Views 1 # 1
Number of Frames Per View 1 # 1
3D Annotations No # 1
Monocular 3D Human Pose Estimation Human3.6M Projected-pose belief maps + 2D fusion layers Average MPJPE (mm) 88.39 # 24
Use Video Sequence No # 1
Frames Needed 1 # 1
Need Ground Truth 2D Pose No # 1

Methods


No methods listed for this paper. Add relevant methods here