Accuracy potential of visual localization exploiting high-end street-level imagery
Overview
This research introduces the FHNW Muttenz dataset, a large-scale outdoor resource covering a contiguous 10 km street network mapped in two campaigns with 5 mm co-registration accuracy. The dataset provides high-resolution reference imagery and query sequences from four cameras, enabling systematic evaluation of sparse feature-based visual localization. Results show that with accurately georeferenced scenes and pre-calibrated cameras, median pose errors are 1-5 cm in translation and 0.03-0.1 degrees in rotation, approaching survey-grade GNSS accuracy while providing full orientation information.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · position accuracy: 6 other · Basis not reported
“r cameras in five scenes. The two campaigns are co-registered to each other with an accuracy of 5 mm. Co-registration of the query images to the reference imagery yields ground-truth poses accurate to 6-9 mm in position and well below 0.1{\deg} in orientation. All images are georeferenced with an accuracy of about 2.5 cm. Second, we use this dataset to systematically evaluate sparse feature-based visual localization”
Exact source · revision 1Source owner not reported
Reported quantity · orientation accuracy: 0.1 other · Basis not reported
“r cameras in five scenes. The two campaigns are co-registered to each other with an accuracy of 5 mm. Co-registration of the query images to the reference imagery yields ground-truth poses accurate to 6-9 mm in position and well below 0.1{\deg} in orientation. All images are georeferenced with an accuracy of about 2.5 cm. Second, we use this dataset to systematically evaluate sparse feature-based visual localization”
Exact source · revision 1Source owner not reported
Reported quantity · georeferencing accuracy: 2.5 other · Basis not reported
“r cameras in five scenes. The two campaigns are co-registered to each other with an accuracy of 5 mm. Co-registration of the query images to the reference imagery yields ground-truth poses accurate to 6-9 mm in position and well below 0.1{\deg} in orientation. All images are georeferenced with an accuracy of about 2.5 cm. Second, we use this dataset to systematically evaluate sparse feature-based visual localization”
Exact source · revision 1Source owner not reported
Reported quantity · translation error: 1 other · Basis not reported
“with a modular pipeline built from established components, using the high-resolution reference imagery directly as the scene representation. For daytime imagery and pre-calibrated cameras, the median pose errors with respect to the reference imagery are 1-5 cm in translation and 0.03-0.1{\deg} in rotation. Given an accurately georeferenced scene representation, visual localization not only approaches the accuracy of”
Exact source · revision 1Source owner not reported
Reported quantity · rotation error: 0.03 other · Basis not reported
“with a modular pipeline built from established components, using the high-resolution reference imagery directly as the scene representation. For daytime imagery and pre-calibrated cameras, the median pose errors with respect to the reference imagery are 1-5 cm in translation and 0.03-0.1{\deg} in rotation. Given an accurately georeferenced scene representation, visual localization not only approaches the accuracy of”
Exact source · revision 1Source owner not reported
Artifact availability · dataset: available
“survey-grade GNSS positioning but also provides full orientation information. The dataset is publicly available at https://fhnw-muttenz-vl-dataset.github.io/”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalAccuracy potential of visual localization exploiting high-end street-level imagery
This research introduces the FHNW Muttenz dataset, a large-scale outdoor resource covering a contiguous 10 km street network mapped in two campaigns with 5 mm co-registration accuracy. The dataset provides high-resolution reference imagery and query sequences from four cameras, enabling systematic evaluation of sparse feature-based visual localization. Results show that with accurately georeferenced scenes and pre-calibrated cameras, median pose errors are 1-5 cm in translation and 0.03-0.1 degrees in rotation, approaching survey-grade GNSS accuracy while providing full orientation information.
Event coverage history
Current attention 3·Peak within the comparable range 4（2026-11-10 16:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).