GRAPH ATTENTION CONVOLUTIONAL NETWORK FOR 3D HUMAN POSE AND SHAPE ESTIMATION FROM POINT CLOUDS

We propose Graph Attention Convolutional Network for 3D human pose and shape estimation. Unlike most deep-learning methods that utilize RGB images as input, we opt for 3D data, believing it can convey richer information. Our method comprises two-stage models. The first, named the Local Joint Network (LJN), employs grouping techniques to gather points and predict 3D joints. The second is Graph Attention Convolutional Network, which takes 3D joints as input, leveraging a combination of Graph Convolutional Neural Networks (GCNNs) and Transformers. The key advantage lies in its consideration of both local and non-local interactions. We acquire point clouds using synthetic data and a Kinect v2 camera. Additionally, for RGB images lacking 3D information, we introduce a Point Cloud Generation System capable of synthesizing 3D data. To the best of our knowledge, we are the first to apply this mechanism to this field.