Super Resolution and Spatial Interpolation
Super resolution is the task to generate higher resolution images from low resolution inputs whereas spatial interpolation is used to generate bitmaps from point measurements based.
Research Focus
Our work on super resolution is on the development of methods to provide meaningful representation for particular down stream task like object detection or segmentation. Furthermore, superresolution methods can be used to provide uniform view on heterogenous and integrated datat sets.
Publications
- Mollière C., Gottfriedsen J., Langer M., Massaro P., Soraruf C. and Schubert M., "Multi-Spectral Super-Resolution of Thermal Infrared Data Products for Urban Heat Applications," IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Pasadena, CA, USA, 2023, pp. 4919-4922, doi: 10.1109/IGARSS52108.2023.10283339.
- Jakaria Rabbi, Nilanjan Ray, Matthias Schubert, Subir Chowdhury, Dennis Chao: Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network. Remote. Sens. 12(9): 1432 (2020)
- Evgeniy Faerman, Manuell Rogalla, Niklas Strauß, Adrian Krüger, Benedict Blümel, Max Berrendorf, Michael Fromm, Matthias Schubert: Spatial Interpolation with Message Passing Framework. ICDM Workshops 2019: 135-141
- Michael Fromm, Max Berrendorf, Evgeniy Faerman, Yiyi Chen, Balthasar Schüss, Matthias Schubert: XD-STOD: Cross-Domain Superresolution for Tiny Object Detection. ICDM Workshops 2019: 142-148