Umar Iqbal, Pavlo Molchanov, Thomas Breuel, Juergen Gall, Jan Kautz
TL;DR本文提出一种使用 2.5D 姿势表示的新方法来从单目图像中估计 3D 手部姿态，通过使用深度图和热力图分布来训练卷积神经网络(CNN) 模型，该模型在多个数据集上实现了最先进 2D 和 3D 手部姿态的估计。
Abstract
Estimating the 3D pose of a hand is an essential part of human-computer interaction. Estimating 3D pose using depth or multi-view sensors has become easier with recent advances in computer vision, however, regressing pose from a single RGB image is much less straightforward. The main difficulty arises from the fact that 3D pose requires some form of depth es