Accuracy potential of visual localization exploiting high-end street-level imagery
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionRobotics
AI summaryⓘ
The authors developed a new system for pinpointing exact locations using high-quality street images, which can help improve positioning in areas where GPS isn't very accurate. They also created a large dataset with very precise location data collected over 10 km of streets at two different times using multiple cameras. By testing their method on this dataset, they showed that visual localization can achieve position accuracies within a few centimeters and very small rotation errors. Their work demonstrates that visual methods can support detailed mapping and navigation alongside traditional GPS. The dataset is publicly available for others to use and study.
Visual localizationPose estimationStructure-from-MotionPnP algorithmGeoreferenced imagery6-DoF poseMobile mappingSurvey-grade accuracyGNSSDataset
Authors
Jonas Meyer, Stephan Nebiker, Pascal Theiler, Norbert Haala
Abstract
Accurate and reliable pose information with respect to a reference frame is increasingly demanded across applications such as autonomous navigation, surveying, robotics, and augmented and mixed reality. Visual localization can serve as a complementary positioning modality to GNSS, whose applicability and accuracy are often limited. Yet, the accuracy potential of visual localization has not been systematically investigated against survey-grade demands. This is mainly due to the lack of publicly available, large-scale outdoor datasets with ground-truth poses in the sub-centimeter range. In this work, we address both gaps. We introduce a scalable visual localization pipeline that employs precisely georeferenced, high-resolution street-level imagery directly as the scene representation. It combines prior-guided reference candidate selection with on-the-fly local Structure-from-Motion reconstruction and PnP-based pose estimation. We further present the FHNW Muttenz dataset, a real-world dataset covering a contiguous 10 km street network mapped in two mobile mapping campaigns approximately 1.5 years apart. It consists of high-resolution reference imagery and query sequences acquired by four different cameras across five representative scenes. All images are precisely co-registered, yielding 6-DoF ground-truth poses in the sub-centimeter range. Using this dataset, we evaluate the accuracy potential of visual localization. Our experiments demonstrate median pose accuracies in the range of 1-5 cm for translation and 0.05-0.1° for rotation, reaching as low as 1 cm and 0.03° under favorable conditions. These results show that visual localization can complement survey-grade GNSS positioning, paving the way for 3D geospatial data acquisition using consumer devices and fully automated georeferencing approaches. The dataset is publicly available at: https://fhnw-muttenz-vl-dataset.github.io/.