In this paper, a feature boosting network is proposed for estimating 3D hand pose and 3D body pose from a single RGB image. In this method, the features learned by the convolutional layers are boosted with a new long short-term dependence-aware (LSTD) module, which enables the intermediate convolutional feature maps to perceive the graphical long short-term dependency among different hand (or body) parts using the designed Graphical ConvLSTM. Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation. To improve the reliability of the features for representing each body part and enhance the LSTD module, we further introduce a context consistency gate (CCG) in this paper, with which the convolutional feature maps are modulated according to their consistency with the context representations. We evaluate the proposed method on challenging benchmark datasets for 3D hand pose estimation and 3D full body pose estimation. Experimental results show the effectiveness of our method that achieves state-of-the-art performance on both of the tasks.

中文翻译：

---

用于 3D 姿态估计的特征增强网络


本文提出了一种特征增强网络，用于从单个 RGB 图像估计 3D 手部姿势和 3D 身体姿势。在该方法中，通过新的长短期依赖性感知（LSTD）模块增强了卷积层学习的特征，该模块使中间卷积特征图能够感知不同手（或身体）之间的图形长期依赖性）部分使用设计的图形ConvLSTM。由于 3D 姿势估计实际应用中的模糊性、纹理和照明变化以及自遮挡，学习一组可靠且有区别地代表手（或身体）部位姿势的特征是很困难的。为了提高表示每个身体部位的特征的可靠性并增强 LSTD 模块，我们在本文中进一步引入了上下文一致性门（CCG），利用该门根据卷积特征图与上下文表示的一致性来调制卷积特征图。我们在具有挑战性的 3D 手部姿势估计和 3D 全身姿势估计基准数据集上评估所提出的方法。实验结果表明我们的方法的有效性，在这两项任务上都实现了最先进的性能。