Saved in:
Bibliographic Details
Main Authors: Zhuang, Xiaoqi, Santos, Jefersson A. Dos, Han, Jungong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.19392
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908983686594560
author Zhuang, Xiaoqi
Santos, Jefersson A. Dos
Han, Jungong
author_facet Zhuang, Xiaoqi
Santos, Jefersson A. Dos
Han, Jungong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19392
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition
Zhuang, Xiaoqi
Santos, Jefersson A. Dos
Han, Jungong
Computer Vision and Pattern Recognition
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.
title HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.19392