Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

Abstract

Various deep learning techniques have been proposedto solve the single-view 2D-to-3D pose estimation problem. While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory. In this work, we target these hard poses and present a novel skeletal GNN learning solution. To be specific, we propose a hop-aware hierarchical channel-squeezing fusion layer to effectively extract relevant information from neighboring nodes while suppressing undesired noises in GNN learning.In addition, we propose a temporal-aware dynamic graph construction procedure that is robust and effective for 3D pose estimation. Experimental results on the Human3.6M dataset show that our solution achieves 10.3% average prediction accuracy improvement and greatly improves on hard poses over state-of-the-art techniques. We further apply the proposed technique on the skeleton-based action recognition task and also achieve state-of-the-art performance. Our code is available at https://github. com/ailingzengzzz/Skeletal-GNN .

Hierarchical Graph Networks for 3D Human Pose Estimation

“…Martinez et al [23] propose a simple yet effective baseline for 3D human pose estimation, it uses only 2D joints as input but gets highly accurate results, showing the importance of 2D joints information for 3D human pose estimation. Since the skeleton's topology can be viewed as a graph structure, there has been increasing use of Graph Convolutional Networks (GCNs) for 2D-to-3D pose estimation tasks [4,19,21,37,40,41].…”