Cascaded deep monocular 3D human pose estimation with evolutionary training data

Abstract

End-to-end deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation, yet these models may fail for unseen poses with limited and fixed training data. This paper proposes a novel data augmentation method that: (1) is scalable for synthesizing massive amount of training data (over 8 million valid 3D human poses with corresponding 2D projections) for training 2D-to-3D networks, (2) can effectively reduce dataset bias. Our method evolves a limited dataset to synthesize unseen 3D human skeletons based on a hierarchical human representation and heuristics inspired by prior knowledge. Extensive experiments show that our approach not only achieves state-of-the-art accuracy on the largest public benchmark, but also generalizes significantly better to unseen and rare poses. Code, pre-trained models and tools are available at this HTTPS URL.

arXiv commentAccepted to CVPR 2020 as Oral Presentation

References in corpus (3)

• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Learning from Synthetic Humans
• Semantic Graph Convolutional Networks for 3D Human Pose Regression

Cited by in corpus (8)

• A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trends
• Vision-Based Human Pose Estimation via Deep Learning: A Survey
• Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation
• Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation
• Dual networks based 3D Multi-Person Pose Estimation from Monocular Video
• View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
• Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Concept
• A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes