论文标题
手工：用于基于深度的3D手姿势估计的简单数据增强方法
HandAugment: A Simple Data Augmentation Method for Depth-Based 3D Hand Pose Estimation
论文作者
论文摘要
从3D深度图像中进行了手动姿势估计，已在计算机视觉领域进行了广泛的探索。但是，基于深度学习的方法最近大大提高了性能，但是由于缺乏大型数据集，例如ImageNet或有效的数据合成方法，该问题仍然无法解决。在本文中，我们提出了掌声，这是一种合成图像数据以增强神经网络训练过程的方法。我们的方法有两个主要部分：首先，我们提出了一个两阶段神经网络的方案。该方案可以使神经网络专注于手部区域，从而提高性能。其次，我们引入了一种简单有效的方法来通过将真实和合成图像组合在一起，以合成数据。最后，我们表明我们的方法在基于深度的3D手姿势估算的任务中获得了第一名。
Hand pose estimation from 3D depth images, has been explored widely using various kinds of techniques in the field of computer vision. Though, deep learning based method improve the performance greatly recently, however, this problem still remains unsolved due to lack of large datasets, like ImageNet or effective data synthesis methods. In this paper, we propose HandAugment, a method to synthesize image data to augment the training process of the neural networks. Our method has two main parts: First, We propose a scheme of two-stage neural networks. This scheme can make the neural networks focus on the hand regions and thus to improve the performance. Second, we introduce a simple and effective method to synthesize data by combining real and synthetic image together in the image space. Finally, we show that our method achieves the first place in the task of depth-based 3D hand pose estimation in HANDS 2019 challenge.
