In this paper, we propose a new architecture called Adaptive Graphical Model
Network (AGMN) to tackle the task of 2D hand pose estimation from a monocular
RGB image. The AGMN consists of two branches of deep convolutional neural
networks for calculating unary and pairwise potential functions, followed by a
graphical model inference module for integrating unary and pairwise potentials.
Unlike existing architectures proposed to combine DCNNs with graphical models,
our AGMN is novel in that the parameters of its graphical model are conditioned
on and fully adaptive to individual input images. Experiments show that our
approach outperforms the state-of-the-art method used in 2D hand keypoints
estimation by a notable margin on two public datasets.

本文提出一种名为自适应图模型网络（AGMN）的新架构，用于从单个 RGB 图像估计 2D 手部姿势，该架构包含两个深度卷积神经网络分支，用于计算一元和双元潜力函数，随后是图形模型推断模块，用于集成一元和双元潜力。与现有的将 DCNN 与图形模型结合的体系结构不同，我们的 AGMN 是新颖的，因为其图形模型的参数是基于并完全适应于个别输入图像的。实验证明，我们的方法在两个公共数据集上比 2D 手关键点估计中使用的最先进方法优越了不少。