Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11919-11928
Abstract
Recently, 3D input data based hand pose estimation methods have shown state-of-the-art performance, because 3D data capture more spatial information than the depth image. Whereas 3D voxel-based methods need a large amount of memory, PointNet based methods need tedious preprocessing steps such as K-nearest neighbour search for each point. In this paper, we present a novel deep learning hand pose estimation method for an unordered point cloud. Our method takes 1024 3D points as input and does not require additional information. We use Permutation Equivariant Layer (PEL) as the basic element, where a residual network version of PEL is proposed for the hand pose estimation task. Furthermore, we propose a voting-based scheme to merge information from individual points to the final pose output. In addition to the pose estimation task, the voting-based scheme can also provide point cloud segmentation result without ground-truth for segmentation. We evaluate our method on both NYU dataset and the Hands2017Challenge dataset, where our method outperforms recent state-of-theart methods.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Online generative model personalization for hand trackingACM Transactions on Graphics, 2017
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation from Single Depth Images2017
- Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs2016
- Training a Feedback Loop for Hand Pose Estimation2015
- Opening the Black Box: Hierarchical Sampling Optimization for Estimating Human Hand Pose2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- Accurate, Robust, and Flexible Real-time Hand Tracking2015
- Real-Time Continuous Pose Recovery of Human Hands Using Convolutional NetworksACM Transactions on Graphics, 2014
- Realtime and Robust Hand Tracking from Depth2014
- Efficient model-based 3D tracking of hand articulations using Kinect2011