Tootfinder

Cross-Dataset Semantic Segmentation Performance Analysis: Unifying NIST Point Cloud City Datasets for 3D Deep Learning
Alexander Nikitas Dimopoulos, Joseph Grasso
https://arxiv.org/abs/2508.00822

Cross-Dataset Semantic Segmentation Performance Analysis: Unifying NIST Point Cloud City Datasets for 3D Deep Learning
This study analyzes semantic segmentation performance across heterogeneously labeled point-cloud datasets relevant to public safety applications, including pre-incident planning systems derived from lidar scans. Using NIST's Point Cloud City dataset (Enfield and Memphis collections), we investigate challenges in unifying differently labeled 3D data. Our methodology employs a graded schema with the KPConv architecture, evaluating performance through IoU metrics on safety-relevant features. Resul…

#PhantastikPrompts  27.7.:
Machst du Ortsbesichtigungen zur Recherche? Nutzt du Fotos oder Ortspläne?
Leider kann ich nicht physisch nach Erytan reisen. Allerdings - und das ist interessant - habe ich zwar beim Schreiben kein visuelles Kopfkino, aber beim Verfassen der Text-RPs das Gefühl, VR-mäßig mitten drin zu sein plus die anderen Sinne.
Ich weiß, wie sich das Pfla…

Frequency Differences between Clocks on the Earth and the Moon
Mingyue Zhang, J\"urgen M\"uller, Sergei M. Kopeikin
https://arxiv.org/abs/2506.16377

Frequency Differences between Clocks on the Earth and the Moon
Based on general relativity, clock comparisons enable the determination of the gravity potential relative to a stable reference. Lunar surface clocks, owing to the Moon's low-noise conditions, high orbital stability, and broad Earth visibility, are promising reference clocks for global-scale comparisons between terrestrial clocks. Meanwhile, the need for an independent lunar time system-driven by future lunar navigation-requires maintaining links to terrestrial standards. This Letter simulates …