PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose
This addresses the challenge of accurate 3D human pose reconstruction from monocular images, which is important for applications like motion analysis and virtual reality, but is incremental as it builds on existing pose-lifting methods.
The study tackled the problem of estimating absolute 3D human poses from single 2D poses by proposing PoseLifter, which achieved state-of-the-art performance in 2D-to-3D lifting and 3D pose estimation on public datasets.
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.