RSEdit: Text-Guided Image Editing for Remote Sensing

TL;DR

This paper introduces RSEdit, a novel framework for text-guided remote sensing image editing, demonstrating superior instruction-faithful edits while maintaining geospatial integrity.

Contribution

It presents the first comprehensive study of conditioning strategies for remote sensing image editing using off-the-shelf text-to-image models.

Findings

RSEdit achieves the best instruction-faithful edits.

It preserves geospatial structure effectively.

The code and checkpoints are publicly released.

Abstract

In this paper, we explore text-guided image editing in the remote sensing domain using generative modeling. We propose \rsedit, a collection of models from U-Net to DiT with various configurations. Specifically, 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 \url{https://github.com/Bili-Sakura/RSEdit-Preview} and checkpoints at \url{https://huggingface.co/collections/BiliSakura/rsedit}.