融合来自运动结构和光流模拟姿势回归的算法用于具有挑战性室内环境（英文版）

英文标题：Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments中文摘要：本文提出了一种使用相对位移回归来规范绝对位姿估计的新方法，采用递归融合神经网络来更好地整合绝对和相对估计姿态，实验结果表明这种方法比使用姿态图优化的方法更为有效。英文摘要：The localization of objects is a crucial task in various applications such asrobotics, virtual and augmented reality, and the transportation of goods inwarehouses. Recent advances in deep learning have enabled the localizationusing monocular visual cameras. While structure from m