Cascaded Deep Monocular 3D Human Pose Estimation With Evolutionary Training Data

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Shichao, Ke, Lei, Pratama, Kevin, Tai, Yu-Wing, Tang, Chi-Keung, Cheng, Kwang-Ting
Format: Conference Proceeding
Language:English
Subjects:
Bones
Pose estimation
Three-dimensional displays
Training
Training data
Two dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. Relevant files and tools are available at the project website.
ISSN:2575-7075
DOI:10.1109/CVPR42600.2020.00621