arXivDaily arXiv每日学术速递 周一至周五更新
看起来今天可以划水了
arXiv 2203.12979cs.CV
收藏

视觉定位中的几何匹配是否足够?

Is Geometry Enough for Matching in Visual Localization?

Technical University of Munich(慕尼黑工业大学);Universidade de Lisboa(里斯本大学)

Qunjie Zhou, Sérgio Agostinho, Aljosa Osep, Laura Leal-Taixé

摘要:

在本文中,我们建议超越成熟的方法,以视觉为基础的本地化,依赖于查询图像和3D点云之间的视觉描述符匹配。虽然通过视觉描述符匹配关键点使定位高度准确,但它具有显著的存储需求,引起了隐私问题,并需要长期更新描述符。为了优雅地解决大规模定位的实际挑战,我们提出了GoMatch,这是一种基于视觉的匹配的替代方案,它仅依赖于将图像关键点与地图匹配的几何信息,表示为一组方位向量。我们新颖的3D点的方位矢量表示,显着缓解了基于几何的匹配中的跨模态挑战,这些挑战阻止了先前的工作在现实环境中解决定位问题。通过额外的精心架构设计,GoMatch改进了先前基于几何的匹配工作,在剑桥地标和7场景上的平均中值姿态误差减少了(10.67m,95.7deg)和(1.43m,34.7deg),同时与最好的基于视觉的匹配方法相比,只需要1.5/1.7%的存储容量。这证实了其在现实世界中的定位的潜力和可行性,并为未来不需要存储视觉描述符的城市规模视觉定位方法的发展打开了大门。

英文摘要:

In this paper, we propose to go beyond the well-established approach to vision-based localization that relies on visual descriptor matching between a query image and a 3D point cloud. While matching keypoints via visual descriptors makes localization highly accurate, it has significant storage demands, raises privacy concerns and requires update to the descriptors in the long-term. To elegantly address those practical challenges for large-scale localization, we present GoMatch, an alternative to visual-based matching that solely relies on geometric information for matching image keypoints to maps, represented as sets of bearing vectors. Our novel bearing vectors representation of 3D points, significantly relieves the cross-modal challenge in geometric-based matching that prevented prior work to tackle localization in a realistic environment. With additional careful architecture design, GoMatch improves over prior geometric-based matching work with a reduction of (10.67m,95.7deg) and (1.43m, 34.7deg) in average median pose errors on Cambridge Landmarks and 7-Scenes, while requiring as little as 1.5/1.7% of storage capacity in comparison to the best visual-based matching methods. This confirms its potential and feasibility for real-world localization and opens the door to future efforts in advancing city-scale visual localization methods that do not require storing visual descriptors.

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。

↑