Year: 2026
Type: article
Abstract: . This paper focuses on cross-modal image matching between Synthetic Aperture Radar (SAR) and optical imagery, a longstanding challenge due to fundamental differences in imaging geometry and radiometry. Beyond applicational needs in satellite data fusion and downstream mapping, this study is motivated by the rapid advances in the field of Computer Vision. Thus, this work evaluates classical and modern learning-based feature matching methods on the renowned SpaceNet9 dataset using a unified evaluation framework. The results show that classical methods such as SIFT fail to produce reliable correspondences, while learning-based approaches, particularly MINIMA, significantly improve performance without additional retraining. However, matching accuracy is strongly influenced by scene structure and SAR-specific geometric effects, therefore robust SAR-optical correspondence remains an open challenge.
Authors: Constantin Günzel, Michael Schmitt
Institution: Universität der Bundeswehr München
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7171790909
FWCI:
Cites:
Cited by:
Related to: