用于二维手部姿态估计的自适应图模型网络
Adaptive Graphical Model Network for 2D Handpose Estimation
AI总结：
针对单目RGB图像的2D手部姿态估计任务，提出一种图模型参数可自适应输入图像的AGMN架构，在两个公开数据集上性能优于现有最优方法。
摘要：
本文提出一种名为自适应图模型网络（Adaptive Graphical Model Network，AGMN）的新型架构，用于解决单目RGB图像的二维手部姿态估计任务。AGMN由两个深度卷积神经网络分支构成，分别用于计算一元势函数和成对势函数，其后接一个图模型推理模块用于整合一元势与成对势。与现有将深度卷积神经网络与图模型结合的架构不同，本文AGMN的创新点在于其图模型的参数以单个输入图像为条件，可完全适配各输入图像。实验表明，本文方法在两个公开数据集上，性能显著优于当前最优的二维手部关键点估计方法。代码可访问https://github.com/deyingk/agmn获取。
英文摘要：
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. Code can be found at https://github.com/deyingk/agmn.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
