3D Human Pose Regression using Graph Convolutional Network
This work addresses 3D human pose estimation for computer vision applications, but it is incremental as it builds on existing graph convolutional methods with minor improvements.
The authors tackled 3D human pose estimation from 2D poses by proposing PoseGraphNet, a graph convolutional network with adaptive adjacency matrices and neighbor-specific kernels, achieving performance close to state-of-the-art on the Human3.6M dataset while using fewer parameters.
3D human pose estimation is a difficult task, due to challenges such as occluded body parts and ambiguous poses. Graph convolutional networks encode the structural information of the human skeleton in the form of an adjacency matrix, which is beneficial for better pose prediction. We propose one such graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses. Our network uses an adaptive adjacency matrix and kernels specific to neighbor groups. We evaluate our model on the Human3.6M dataset which is a standard dataset for 3D pose estimation. Our model's performance is close to the state-of-the-art, but with much fewer parameters. The model learns interesting adjacency relations between joints that have no physical connections, but are behaviorally similar.