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

TL;DR

This paper introduces a scalable data augmentation method for monocular 3D human pose estimation that synthesizes vast amounts of training data, improving accuracy and generalization to unseen poses.

Contribution

The proposed hierarchical evolution-based data augmentation method effectively generates diverse training data, reducing dataset bias and enhancing model generalization for 3D human pose estimation.

Findings

Achieves state-of-the-art accuracy on large benchmark datasets.

Significantly improves generalization to unseen and rare poses.

Synthesizes over 8 million valid 3D poses for training.

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.