HandAugment: A Simple Data Augmentation for HANDS19 Challenge Task 1 -- Depth-Based 3D Hand Pose Estimation

Hand pose estimation from 3D depth images, has been explored widely using various kinds of techniques in the field of computer vision. However, this problem still remain unsolved. In this paper we present HandAugment, a simple data augmentation for depth-based 3D hand pose estimation. HandAugment consists of two stages of neural networks. The first stage of neural network is used to extract hand patches and estimate the initial hand poses from the depth images in an iteration fashion. This step can help filter out more outlier patches away (e.g., arms and backgrounds). Then the extracted patches and initial hand poses are further feed into the neural network of the second stage to get the final hand poses. This strategy of two stages greatly improves the accuracy of hands pose estimation. Finally, our method achieves the first place in the task of depth-based 3D hand pose estimation in HANDS19 challenge.