Graph U-Shaped Network with Mapping-Aware Local Enhancement for Single-Frame 3D Human Pose Estimation

Abstract

The development of 2D-to-3D approaches for 3D monocular single-frame human pose estimation faces challenges related to noisy input and failure to capture long-range joint correlations, leading to unreasonable predictions. To this end, we propose a straightforward, but effective U-shaped network called the mapping-aware U-shaped graph convolutional network (M-UGCN) for single-frame applications. This network applies skeletal pooling/unpooling operations to expand the limited convolutional receptive field. For noisy inputs, as local nodes have direct access to the subtle discrepancies between poses, we define an additional mapping-aware local-enhancement mechanism to focus on local node interactions across multiple scales. We evaluated our proposed method on the benchmark datasets Human3.6M and MPI-INF-3DHP, and the experimental results demonstrated the robustness of the M-UGCN against noisy inputs. Notably, the average error in the proposed method was found to be 4.1% lower when compared to state-of-the-art methods adopting similar multi-scale learning approaches.