PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning
This addresses the data scarcity and generalization issues in 3D pose estimation for computer vision applications, representing a novel method for a known bottleneck.
The authors tackled the problem of poor generalization in 3D human pose estimation due to limited training data diversity by proposing PoseGU, a novel human pose generator that uses a small seed set and unbiased learning, resulting in outperforming state-of-the-art methods on three benchmark datasets.
3D pose estimation has recently gained substantial interests in computer vision domain. Existing 3D pose estimation methods have a strong reliance on large size well-annotated 3D pose datasets, and they suffer poor model generalization on unseen poses due to limited diversity of 3D poses in training sets. In this work, we propose PoseGU, a novel human pose generator that generates diverse poses with access only to a small size of seed samples, while equipping the Counterfactual Risk Minimization to pursue an unbiased evaluation objective. Extensive experiments demonstrate PoseGU outforms almost all the state-of-the-art 3D human pose methods under consideration over three popular benchmark datasets. Empirical analysis also proves PoseGU generates 3D poses with improved data diversity and better generalization ability.