3D Human Pose Estimation with Relational Networks
arXiv:1805.08961
Abstract
In this paper, we propose a novel 3D human pose estimation algorithm from a single image based on neural networks. We adopted the structure of the relational networks in order to capture the relations among different body parts. In our method, each pair of different body parts generates features, and the average of the features from all the pairs are used for 3D pose estimation. In addition, we propose a dropout method that can be used in relational modules, which inherently imposes robustness to the occlusions. The proposed network achieves state-of-the-art performance for 3D pose estimation in Human 3.6M dataset, and it effectively produces plausible results even in the existence of missing joints.
arXiv commentBMVC 2018, source code: https://github.com/sungheonpark/3D_HPE_RN
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Deep Residual Learning for Image Recognition
- Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
- Stacked Hourglass Networks for Human Pose Estimation
- A simple neural network module for relational reasoning
- Compositional Human Pose Regression
- Structured Prediction of 3D Human Pose with Deep Neural Networks
- Unite the People: Closing the Loop Between 3D and 2D Human Representations
- 3D Human Pose Estimation in the Wild by Adversarial Learning
- Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation
- Deep Pose Consensus Networks