PoseGraphNet++: Enriching 3D Human Pose with Orientation Estimation

TL;DR

PoseGraphNet++ advances 3D human pose estimation by jointly predicting joint positions and bone orientations using a graph convolution network, achieving balanced and improved accuracy over state-of-the-art methods.

Contribution

It introduces a novel graph convolutional approach that predicts complete human pose including orientations, addressing the unresolved roll angle in prior methods.

Findings

Performs on par with state-of-the-art on Human3.6M for position and orientation.

Achieves best generalization results in position estimation.

Utilizes joint and bone features for significantly improved predictions.

Abstract

Existing skeleton-based 3D human pose estimation methods only predict joint positions. Although the yaw and pitch of bone rotations can be derived from joint positions, the roll around the bone axis remains unresolved. We present PoseGraphNet++ (PGN++), a novel 2D-to-3D lifting Graph Convolution Network that predicts the complete human pose in 3D including joint positions and bone orientations. We employ both node and edge convolutions to utilize the joint and bone features. Our model is evaluated on multiple datasets using both position and rotation metrics. PGN++ performs on par with the state-of-the-art (SoA) on the Human3.6M benchmark. In generalization experiments, it achieves the best results in position and matches the SoA in orientation, showcasing a more balanced performance than the current SoA. PGN++ exploits the mutual relationship of joints and bones resulting in significantly \SB{improved} position predictions, as shown by our ablation results.