Multi-View Matching Network for 6D Pose Estimation

Multi-View Matching Network for 6D Pose Estimation
复制标题

用于 6D 姿态估计的多视图匹配网络

DOI:
--
复制
发表时间:
2019
期刊:
arXiv.org
影响因子:
--
通讯作者:
E. Delp
E. Delp
中科院分区:
--
文献类型:
--
作者:
D. M. Montserrat;Jianhang Chen;Qian Lin;J. Allebach;E. Delp

文献摘要

被引文献

相似文献

与真实的世界交互的应用程序(如增强现实或机器人操作)需要很好地理解周围物体的位置和姿态。在本文中,我们提出了一种新的方法来估计6自由度(DoF)或6D姿态的对象从一个单一的RGB图像。我们的方法可以与对象检测和分割方法配对,通过将输入图像与渲染图像进行匹配来估计、细化和跟踪对象的姿态。
Applications that interact with the real world such as augmented reality or robot manipulation require a good understanding of the location and pose of the surrounding objects. In this paper, we present a new approach to estimate the 6 Degree of Freedom (DoF) or 6D pose of objects from a single RGB image. Our approach can be paired with an object detection and segmentation method to estimate, refine and track the pose of the objects by matching the input image with rendered images.