Exploring Text-Guided Single Image Editing for Remote Sensing Images

TL;DR

This paper introduces a novel text-guided single-image editing method for remote sensing images that operates with minimal training data, leveraging pre-trained vision-language models and prompt ensembling to improve accuracy and controllability.

Contribution

It proposes a new RSI editing approach using only one image for training, employing multi-scale training and prompt ensembling to overcome dataset limitations and semantic ambiguity.

Findings

Outperforms existing methods in CLIP scores

Achieves high subjective quality in edits

Supports practical disaster assessment tasks

Abstract

Artificial intelligence generative content (AIGC) has significantly impacted image generation in the field of remote sensing. However, the equally important area of remote sensing image (RSI) editing has not received sufficient attention. Deep learning based editing methods generally involve two sequential stages: generation and editing. For natural images, these stages primarily rely on generative backbones pre-trained on large-scale benchmark datasets and text guidance facilitated by vision-language models (VLMs). However, it become less viable for RSIs: First, existing generative RSI benchmark datasets do not fully capture the diversity of RSIs, and is often inadequate for universal editing tasks. Second, the single text semantic corresponds to multiple image semantics, leading to the introduction of incorrect semantics. To solve above problems, this paper proposes a text-guided RSI editing method and can be trained using only a single image. A multi-scale training approach is adopted to preserve consistency without the need for training on extensive benchmarks, while leveraging RSI pre-trained VLMs and prompt ensembling (PE) to ensure accuracy and controllability. Experimental results on multiple RSI editing tasks show that the proposed method offers significant advantages in both CLIP scores and subjective evaluations compared to existing methods. Additionally, we explore the ability of the edited RSIs to support disaster assessment tasks in order to validate their practicality. Codes will be released at https://github.com/HIT-PhilipHan/remote_sensing_image_editing.