DRPose3D: Depth Ranking in 3D Human Pose Estimation

DRPose3D: Depth Ranking in 3D Human Pose Estimation

Min Wang, Xipeng Chen, Wentao Liu, Chen Qian, Liang Lin, Lizhuang Ma

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 978-984. https://doi.org/10.24963/ijcai.2018/136

In this paper, we propose a two-stage depth ranking based method (DRPose3D) to tackle the problem of 3D human pose estimation. Instead of accurate 3D positions, the depth ranking can be identified by human intuitively and learned using the deep neural network more easily by solving classification problems. Moreover, depth ranking contains rich 3D information. It prevents the 2D-to-3D pose regression in two-stage methods from being ill-posed. In our method, firstly, we design a Pairwise Ranking Convolutional Neural Network (PRCNN) to extract depth rankings of human joints from images. Secondly, a coarse-to-fine 3D Pose Network(DPNet) is proposed to estimate 3D poses from both depth rankings and 2D human joint locations. Additionally, to improve the generality of our model, we introduce a statistical method to augment depth rankings. Our approach outperforms the state-of-the-art methods in the Human3.6M benchmark for all three testing protocols, indicating that depth ranking is an essential geometric feature which can be learned to improve the 3D pose estimation.
Keywords:
Machine Learning: Deep Learning
Computer Vision: 2D and 3D Computer Vision
Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation
Computer Vision: Biometrics, Face and Gesture Recognition
Computer Vision: Computer Vision