SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space

TL;DR

SPGNet introduces a novel 3D human pose estimation method that integrates multi-dimensional re-projection and kinematic constraints, achieving superior accuracy on the Human3.6M dataset.

Contribution

The paper presents a new approach combining re-projection and kinematic constraints for improved 3D pose estimation in low-dimensional space.

Findings

Outperforms state-of-the-art methods on Human3.6M dataset

Effective use of re-projection for pose consistency

Kinematic constraints improve prediction accuracy

Abstract

We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning. In this method, the 2D-to-3D-lifting network predicts the global position and coordinates of the 3D human pose. Then, we re-project the estimated 3D pose back to the 2D key points along with spatial adjustments. The loss functions compare the estimated 3D pose with the 3D pose ground truth, and re-projected 2D pose with the input 2D pose. In addition, we propose a kinematic constraint to restrict the predicted target with constant human bone length. Based on the estimation results for the dataset Human3.6M, our approach outperforms many state-of-the-art methods both qualitatively and quantitatively.