Augmented Skeleton Space Transfer for Depth-based Hand Pose Estimation
Preprint
Abstract
Crucial to the success of training a depth-based 3D hand pose estimator (HPE) is the availability of comprehensive datasets covering diverse camera perspectives, shapes, and pose variations. However, collecting such annotated datasets is challenging. We propose to complete existing databases by generating new database entries. The key idea is to synthesize data in the skeleton space (instead of doing so in the depth-map space) which enables an easy and intuitive way of manipulating data entries. Since the skeleton entries generated in this way do not have the corresponding depth map entries, we exploit them by training a separate hand pose generator (HPG) which synthesizes the depth map from the skeleton entries. By training the HPG and HPE in a single unified optimization framework enforcing that 1) the HPE agrees with the paired depth and skeleton entries; and 2) the HPG-HPE combination satisfies the cyclic consistency (both the input and the output of HPG-HPE are skeletons) observed via the newly generated unpaired skeletons, our algorithm constructs a HPE which is robust to variations that go beyond the coverage of the existing database. Our training algorithm adopts the generative adversarial networks (GAN) training process. As a by-product, we obtain a hand pose discriminator (HPD) that is capable of picking out realistic hand poses. Our algorithm exploits this capability to refine the initial skeleton estimates in testing, further improving the accuracy. We test our algorithm on four challenging benchmark datasets (ICVL, MSRA, NYU and Big Hand 2.2M datasets) and demonstrate that our approach outperforms or is on par with state-of-the-art methods quantitatively and qualitatively.Keywords
All Related Versions
This publication has 47 references indexed in Scilit:
- Learning a deep network with spherical part model for 3D hand pose estimationPattern Recognition, 2018
- Guided optimisation through classification and regression for hand pose estimationComputer Vision and Image Understanding, 2017
- Real-Time Joint Tracking of a Hand Manipulating an Object from RGB-D Input2016
- Hand Pose Estimation from Local Surface Normals2016
- Spatial Attention Deep Net with Partial PSO for Hierarchical Hybrid Hand Pose Estimation2016
- Multi-view 3D Models from Single Images with a Convolutional Network2016
- Cascaded hand pose regression2015
- Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture2014
- The Vitruvian manifold: Inferring dense correspondences for one-shot human pose estimation2012
- Hand Pose Estimation and Hand Shape Classification Using Multi-layered Randomized Decision Forests2012