IEEE Trans Pattern Anal Mach Intell. 2022 Apr;44(4):2074-2088. doi: 10.1109/TPAMI.2020.3032010. Epub 2022 Mar 4.
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing conditions, including day-night changes, as well as weather and seasonal variations, while providing highly accurate six degree-of-freedom (6DOF) camera pose estimates. In this paper, we extend three publicly available datasets containing images captured under a wide variety of viewing conditions, but lacking camera pose information, with ground truth pose information, making evaluation of the impact of various factors on 6DOF camera pose estimation accuracy possible. We also discuss the performance of state-of-the-art localization approaches on these datasets. Additionally, we release around half of the poses for all conditions, and keep the remaining half private as a test set, in the hopes that this will stimulate research on long-term visual localization, learned local image features, and related research areas. Our datasets are available at visuallocalization.net, where we are also hosting a benchmarking server for automatic evaluation of results on the test set. The presented state-of-the-art results are to a large degree based on submissions to our server.
视觉定位使自动驾驶汽车能够在其周围环境中导航，增强现实应用程序将虚拟世界与现实世界联系起来。实用的视觉定位方法需要能够应对各种不同的观察条件，包括昼夜变化，以及天气和季节变化，同时提供高度准确的六自由度（6DOF）相机姿态估计。在本文中，我们扩展了三个公开数据集，这些数据集包含在各种观察条件下拍摄的图像，但缺少相机姿态信息，我们提供了地面真实姿态信息，从而可以评估各种因素对 6DOF 相机姿态估计精度的影响。我们还讨论了最先进的定位方法在这些数据集上的性能。此外，我们还发布了所有条件下一半的姿态，另一半作为测试集保留私有，希望这将激发对长期视觉定位、学习局部图像特征和相关研究领域的研究。我们的数据集可在 visuallocalization.net 上获得，我们还在该网站上托管了一个基准测试服务器，用于自动评估测试集上的结果。所呈现的最先进的结果在很大程度上基于我们服务器上的提交。
