无需训练即可实现卫星图像无缝拼接，提升遥感合成效率。
HarmoniDiff-RS: Training-Free Diffusion Harmonization for Satellite Image Composition
- 通过潜在空间均值迁移，实现不同卫星图像间的辐射特征对齐。
- 结合早期与晚期潜在表示，生成多组候选图像并自动筛选最优结果。
- 适用于遥感数据增强、灾害模拟等需要大规模图像合成的场景。
卫星图像拼接在遥感应用中至关重要，如数据增强、灾害模拟和城市规划。本文提出 HarmoniDiff-RS，一种无需训练的基于扩散模型的卫星图像和谐化框架，可在多种域条件下实现图像融合。方法通过潜在均值迁移操作，将源域与目标域的辐射特性对齐；为平衡和谐化效果与内容保真度，采用分时潜空间融合策略，利用早期反演潜空间实现高和谐化，晚期潜空间保持语义一致性，生成多组候选图像；再通过轻量级和谐分类器自动选择最连贯的结果。此外，构建了基于 fMoW 的基准数据集 RSIC-H，包含 500 对配对拼接样本。实验表明，该方法能有效完成卫星图像拼接，具备强大的可扩展性，适用于大规模遥感合成与仿真任务。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。