RSEdit: Text-Guided Image Editing for Remote Sensing
IEEE Geoscience and Remote Sensing Letters · 2026 · 23 · 6011905-6011905
DOI: 10.1109/lgrs.2026.3695484 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Geoscience and Remote Sensing Letters, 2026. Verfasst von Zhenyuan Chen und 2 weiteren Autor:innen. Die Arbeit nennt 18 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In this letter, we explore text-guided image editing in the remote sensing (RS) domain using generative modeling. We propose RSEdit, a collection of models from U-Net to diffusion transformer (DiT) with various configurations. In particular, we present the first comprehensive study of conditioning strategies for building image-editing models from off-the-shelf text-to-image ones. Our experiments show that RSEdit achieves the best instruction-faithful edits while preserving geospatial structure. We release the code at https://github.com/Bili-Sakura/RSEdit-Preview and the checkpoints at https://huggingface.co/collections/BiliSakura/rsedit
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Chen, Z., Zhang, Z., & Zhang, F. (2026). RSEdit: Text-Guided Image Editing for Remote Sensing. IEEE Geoscience and Remote Sensing Letters, 23, 6011905-6011905. https://doi.org/10.1109/lgrs.2026.3695484
Vancouver
Chen Z, Zhang Z, Zhang F. RSEdit: Text-Guided Image Editing for Remote Sensing. IEEE Geoscience and Remote Sensing Letters. 2026;23:6011905-6011905. doi:10.1109/lgrs.2026.3695484
BibTeX
@article{Chen2026,
author = {Chen, Zhenyuan and Zhang, Zechuan and Zhang, Feng},
title = {RSEdit: Text-Guided Image Editing for Remote Sensing},
journal = {IEEE Geoscience and Remote Sensing Letters},
year = {2026},
volume = {23},
pages = {6011905--6011905},
doi = {10.1109/lgrs.2026.3695484}
}
EUVIMED