HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition

TL;DR

HarmoniDiff-RS is a training-free diffusion framework for satellite image harmonization that aligns domain radiometric features and preserves content, demonstrated on a new benchmark dataset.

Contribution

It introduces a novel training-free diffusion-based approach with a latent mean shift and fusion strategy for satellite image harmonization, along with a new benchmark dataset.

Findings

Effective in harmonizing satellite images across diverse domains.

Outperforms existing methods in maintaining content and radiometric consistency.

Code and dataset facilitate future research in satellite image synthesis.

Abstract

Satellite image composition plays a critical role in remote sensing applications such as data augmentation, disaste simulation, and urban planning. We propose HarmoniDiff-RS, a training-free diffusion-based framework for harmonizing composite satellite images under diverse domain conditions. Our method aligns the source and target domains through a Latent Mean Shift operation that transfers radiometric characteristics between them. To balance harmonization and content preservation, we introduce a Timestep-wise Latent Fusion strategy by leveraging early inverted latents for high harmonization and late latents for semantic consistency to generate a set of composite candidates. A lightweight harmony classifier is trained to further automatically select the most coherent result among them. We also construct RSIC-H, a benchmark dataset for satellite image harmonization derived from fMoW, providing 500 paired composition samples. Experiments demonstrate that our method effectively performs satellite image composition, showing strong potential for scalable remote-sensing synthesis and simulation tasks. Code is available at: https://github.com/XiaoqiZhuang/HarmoniDiff-RS.