一篇2018年的关于3D hand pose的综述，作为入门了解hand pose领域，快速掌握热点应该比较有帮助。

论文地址：link

a b s t r a c t

3D Hand pose estimation has received an increasing amount of attention, especially since consumer depth cameras came onto the market in 2010. Although substantial progress has occurred recently, no overview has kept up with the latest developments. To bridge the gap, we provide a comprehensive sur- vey, including depth cameras, hand pose estimation methods, and public benchmark datasets. First, a markerless approach is proposed to evaluate the tracking accuracy of depth cameras with the aid of a numerical control linear motion guide. Traditional approaches focus only on static characteristics. The evaluation of dynamic tracking capability has been long neglected. Second, we summarize the state-of- the-art methods and analyze the lines of research. Third, existing benchmark datasets and evaluation criteria are identified to provide further insight into the field of hand pose estimation. In addition, re- alistic challenges, recent trends, dataset creation and annotation, and open problems for future research directions are also discussed.

Abstract

这篇文章提供了包括深度相机，手势估计方法和公共基准数据集的review。主要内容有：

  • 首先，提出了一种无标记方法，借助数控线性运动导轨来评估深度相机的跟踪精度。传统方法仅关注静态特性。动态跟踪能力的评估长期以来一直被忽略。
  • 其次，总结了最先进的方法并分析了研究方向。
  • 第三，确定现有的基准数据集benchmark datasets和评估标准evaluation

Introduction

大体介绍了手势估计的主要应用：

virtual reality (VR) and augmented reality (AR), gesture recognition [3] , interactive games [4–7] , user interface controls [8–11] , computer-aided design (CAD) [12] , hand shape personalization [13–16] , sign languages [17–19] , mid-air interaction [20–22] , action recognition

主要说了下深度相机的应用前景，并且说本文提出了一种测量提出动态追踪准确率的方法

Related work

提到了之前做的一些review，并提到概括了上百种method和22个数据集

101 state-of-the-art methods and 22 datasets are summarized in the form of tables

Problem formulation

问题阐述这部分，