跨模态遥感图像翻译框架，提升红外、可见光与雷达图像转换质量。
EarthBridge: A Solution for 4th Multi-modal Aerial View Image Challenge Translation Track
- 采用非马尔可夫桥过程与对比学习，实现高保真图像生成。
- 在四项任务中均表现优异，综合得分0.38，排名第二。
- 适合遥感图像处理、多模态感知研究者参考。
电光（EO）、红外（IR）与合成孔径雷达（SAR）传感器之间的跨模态图像翻译对全面的多模态航空图像分析至关重要。然而，由于电磁特征和几何特性差异，跨模态转换极具挑战。本文提出EarthBridge框架，用于第四届多模态航空图像挑战赛——翻译赛道（MAVIC-T）。我们探索两种方法：基于非马尔可夫桥过程的扩散桥隐式模型（DBIM），支持高质量确定性采样；以及利用对比学习保持结构一致性的无配对翻译（CUT）。EarthBridge采用通道拼接的UNet去噪器，结合Karras加权桥缩放与特殊“启动噪声”初始化，以应对跨模态映射中的固有模糊性。在所有四项任务（SAR→EO、SAR→RGB、SAR→IR、RGB→IR）上评估，均实现优异的空间细节与光谱准确性。最终综合得分0.38，位列MAVIC-T排行榜第二。代码已开源：https://github.com/Bili-Sakura/EarthBridge-Preview。
原文摘要 · Abstract (English)
Cross-modal image-to-image translation among Electro-Optical (EO), Infrared (IR), and Synthetic Aperture Radar (SAR) sensors is essential for comprehensive multi-modal aerial-view analysis. However, translating between these modalities is notoriously difficult due to their distinct electromagnetic signatures and geometric characteristics. This paper presents \textbf{EarthBridge}, a high-fidelity translation framework developed for the 4th Multi-modal Aerial View Image Challenge -- Translation (MAVIC-T). We explore two distinct methodologies: \textbf{Diffusion Bridge Implicit Models (DBIM)}, which we generalize using non-Markovian bridge processes for high-quality deterministic sampling, and \textbf{Contrastive Unpaired Translation (CUT)}, which utilizes contrastive learning for structural consistency. Our EarthBridge framework employs a channel-concatenated UNet denoiser trained with Karras-weighted bridge scalings and a specialized "booting noise" initialization to handle the inherent ambiguity in cross-modal mappings. We evaluate these methods across all four challenge tasks (SAR$\rightarrow$EO, SAR$\rightarrow$RGB, SAR$\rightarrow$IR, RGB$\rightarrow$IR), achieving superior spatial detail and spectral accuracy. Our solution achieved a composite score of 0.38, securing the second position on the MAVIC-T leaderboard. Code is available at https://github.com/Bili-Sakura/EarthBridge-Preview.
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。