PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation

Abstract

Existing 3D human pose estimators suffer poor generalization performance to new datasets, largely due to the limited diversity of 2D-3D pose pairs in the training data. To address this problem, we present PoseAug, a new auto-augmentation framework that learns to augment the available training poses towards a greater diversity and thus improve generalization of the trained 2D-to-3D pose estimator. Specifically, PoseAug introduces a novel pose augmentor that learns to adjust various geometry factors (e.g., posture, body size, view point and position) of a pose through differentiable operations. With such differentiable capacity, the augmentor can be jointly optimized with the 3D pose estimator and take the estimation error as feedback to generate more diverse and harder poses in an online manner. Moreover, PoseAug introduces a novel part-aware Kinematic Chain Space for evaluating local joint-angle plausibility and develops a discriminative module accordingly to ensure the plausibility of the augmented poses. These elaborate designs enable PoseAug to generate more diverse yet plausible poses than existing offline augmentation methods, and thus yield better generalization of the pose estimator. PoseAug is generic and easy to be applied to various 3D pose estimators. Extensive experiments demonstrate that PoseAug brings clear improvements on both intra-scenario and cross-scenario datasets. Notably, it achieves 88.6% 3D PCK on MPI-INF-3DHP under cross-dataset evaluation setup, improving upon the previous best data augmentation based method by 9.1%. Code can be found at: https://github.com/jfzhang95/PoseAug.

arXiv commentCVPR 2021 Oral Paper, code available: https://github.com/jfzhang95/PoseAug

References in corpus (10)

• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Learning from Synthetic Humans
• MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
• A simple yet effective baseline for 3d human pose estimation
• Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
• OriNet: A Fully Convolutional Network for 3D Human Pose Estimation
• Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
• 3D Human Pose Estimation in the Wild by Adversarial Learning
• Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop