Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimation
This addresses the challenge of accurate biomechanical gait analysis for healthcare applications, though it is incremental in improving cross-view generalization.
The paper tackles the problem of 3D human pose estimation from depth images under occlusions and viewpoint changes, proposing a novel approach that achieves superior performance on gait analysis datasets and produces more convincing keypoints than ground truth on the ITOP dataset.
Accurate estimation of three-dimensional human skeletons from depth images can provide important metrics for healthcare applications, especially for biomechanical gait analysis. However, there exist inherent problems associated with depth images captured from a single view. The collected data is greatly affected by occlusions where only partial surface data can be recorded. Furthermore, depth images of human body exhibit heterogeneous characteristics with viewpoint changes, and the estimated poses under local coordinate systems are expected to go through equivariant rotations. Most existing pose estimation models are sensitive to both issues. To address this, we propose a novel approach for cross-view generalization with an occlusion-invariant semi-supervised learning framework built upon a novel rotation-equivariant backbone. Our model was trained with real-world data from a single view and unlabelled synthetic data from multiple views. It can generalize well on the real-world data from all the other unseen views. Our approach has shown superior performance on gait analysis on our ICL-Gait dataset compared to other state-of-the-arts and it can produce more convincing keypoints on ITOP dataset, than its provided "ground truth".