3 papers
cs.CV2026
Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data
Mojgan Madadikhaljan, Jonathan Prexl, Isabelle Wittmann +2
In this work, we present LIANet (Location Is All You Need Network), a coordinate-based neural representation that models multi-temporal spaceborne Earth observation (EO) data for a…
cs.CV2025
SARFormer -- An Acquisition Parameter Aware Vision Transformer for Synthetic Aperture Radar Data
Jonathan Prexl, Michael Recla, Michael Schmitt
This manuscript introduces SARFormer, a modified Vision Transformer (ViT) architecture designed for processing one or multiple synthetic aperture radar (SAR) images. Given the comp…
cs.LG2025
Better, Not Just More: Data-Centric Machine Learning for Earth Observation
Ribana Roscher, Marc RuÃwurm, Caroline Gevaert +8
Recent developments and research in modern machine learning have led to substantial improvements in the geospatial field. Although numerous deep learning architectures and models h…