PoseGraphNet++: Enriching 3D Human Pose with Orientation Estimation
This addresses the limitation in skeleton-based 3D human pose estimation for applications like animation or robotics, though it is incremental as it builds on prior graph convolution networks.
The paper tackles the problem of 3D human pose estimation by predicting both joint positions and bone orientations, which existing methods lack for roll rotation. It achieves state-of-the-art performance on the Human3.6M benchmark and shows balanced results in generalization experiments.
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.