论文标题
SIA-GCN：具有2D卷积的空间信息意识到的图形神经网络，用于手工姿势估计
SIA-GCN: A Spatial Information Aware Graph Neural Network with 2D Convolutions for Hand Pose Estimation
论文作者
论文摘要
图形神经网络（GNNS）将神经网络从常规结构上的应用程序推广到任意图上的应用，并在许多应用领域（例如计算机视觉，社交网络和化学）中显示出成功。在本文中，我们沿两个方向扩展了GNN：a）允许每个节点的特征由2D空间置信图表示，而不是1D向量； b）提出一个有效的操作，以通过在每个边缘的不同可学习的内核将相邻节点的信息集成到来自相邻节点的信息。所提出的SIA-GCN可以从每个节点的2D地图中有效提取空间信息，并通过图形卷积传播它们。通过将每个边缘与指定的卷积内核相关联，SIA-GCN可以捕获不同对相邻节点的不同空间关系。我们演示了SIA-GCN在估算单帧图像的手关键点的任务上的实用性，其中节点代表关键点的2D坐标热图，而边缘表示关键点之间的动力学关系。多个数据集上的实验表明，SIA-GCN提供了一个灵活但功能强大的框架，以说明关键点之间的结构约束，并可以在手工姿势估计的任务上实现最新的性能。
Graph Neural Networks (GNNs) generalize neural networks from applications on regular structures to applications on arbitrary graphs, and have shown success in many application domains such as computer vision, social networks and chemistry. In this paper, we extend GNNs along two directions: a) allowing features at each node to be represented by 2D spatial confidence maps instead of 1D vectors; and b) proposing an efficient operation to integrate information from neighboring nodes through 2D convolutions with different learnable kernels at each edge. The proposed SIA-GCN can efficiently extract spatial information from 2D maps at each node and propagate them through graph convolution. By associating each edge with a designated convolution kernel, the SIA-GCN could capture different spatial relationships for different pairs of neighboring nodes. We demonstrate the utility of SIA-GCN on the task of estimating hand keypoints from single-frame images, where the nodes represent the 2D coordinate heatmaps of keypoints and the edges denote the kinetic relationships between keypoints. Experiments on multiple datasets show that SIA-GCN provides a flexible and yet powerful framework to account for structural constraints between keypoints, and can achieve state-of-the-art performance on the task of hand pose estimation.
