PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose
This study presents a new network (i.e., PoseLifter) that can lift a 2D human pose to an absolute 3D pose in a camera coordinate system. The proposed network estimates the absolute 3D location of a target subject and generates an improved 3D relative pose estimation compared with existing pose-lifting methods. Using the PoseLifter with a 2D pose estimator in a cascade fashion can estimate a 3D human pose from a single RGB image. In this case, we empirically prove that using realistic 2D poses synthesized with the real error distribution of 2D body joints considerably improves the performance of our PoseLifter. The proposed method is applied to public datasets to achieve state-of-the-art 2D-to-3D pose lifting and 3D human pose estimation.
PDF Abstract
Datasets
MS COCO
Human3.6M
MPII
MPI-INF-3DHP
Results from the Paper
Ranked #49 on
3D Human Pose Estimation
on MPI-INF-3DHP
(PCK metric)
