OpenStreetView-5M:通往全球视觉地理定位的众多道路
OpenStreetView-5M: The Many Roads to Global Visual Geolocation
AI总结:
本文提出大规模开放获取街景数据集OpenStreetView-5M,包含超510万张覆盖225国地区的地理参考图像,通过严格训练测试分离评估视觉地理定位算法,并广泛基准测试了多种图像编码器与训练策略。
摘要:
确定图像在地球上任意位置是一项复杂的视觉任务,这使其与评估计算机视觉算法高度相关。然而,缺乏标准、大规模、开放获取且包含可靠可定位图像的数据集限制了其潜力。为解决此问题,我们引入了OpenStreetView-5M,这是一个大规模、开放获取的数据集,包含超过510万张地理参考街景图像,覆盖225个国家和地区。与现有基准不同,我们实施了严格的训练/测试集分离,使我们能够评估学习到的地理特征的相关性,而不仅仅是记忆。为证明数据集的实用性,我们对各种最先进的图像编码器、空间表示和训练策略进行了广泛基准测试。所有相关代码和模型可在https://github.com/gastruc/osv5m找到。
英文摘要:
Determining the location of an image anywhere on Earth is a complex visual task, which makes it particularly relevant for evaluating computer vision algorithms. Yet, the absence of standard, large-scale, open-access datasets with reliably localizable images has limited its potential. To address this issue, we introduce OpenStreetView-5M, a large-scale, open-access dataset comprising over 5.1 million geo-referenced street view images, covering 225 countries and territories. In contrast to existing benchmarks, we enforce a strict train/test separation, allowing us to evaluate the relevance of learned geographical features beyond mere memorization. To demonstrate the utility of our dataset, we conduct an extensive benchmark of various state-of-the-art image encoders, spatial representations, and training strategies. All associated codes and models can be found at https://github.com/gastruc/osv5m.
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。