GraFormer: Graph Convolution Transformer for 3D Pose Estimation
This work addresses pose estimation for computer vision applications, offering an incremental improvement in efficiency and performance.
The paper tackles the problem of 2D-to-3D pose estimation by proposing GraFormer, a transformer combined with graph convolution, which outperforms state-of-the-art methods on the Human3.6M dataset while using 18% fewer parameters.
Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation. To alleviate this issue, we propose GraFormer, a novel transformer architecture combined with graph convolution for 3D pose estimation. The proposed GraFormer comprises two repeatedly stacked core modules, GraAttention and ChebGConv block. GraAttention enables all 2D joints to interact in global receptive field without weakening the graph structure information of joints, which introduces vital features for later modules. Unlike vanilla graph convolutions that only model the apparent relationship of joints, ChebGConv block enables 2D joints to interact in the high-order sphere, which formulates their hidden implicit relations. We empirically show the superiority of GraFormer through conducting extensive experiments across popular benchmarks. Specifically, GraFormer outperforms state of the art on Human3.6M dataset while using 18$\%$ parameters. The code is available at https://github.com/Graformer/GraFormer .