EarthMapper：用于可控双向卫星图-地图翻译的视觉自回归模型
EarthMapper: Visual Autoregressive Models for Controllable Bidirectional Satellite-Map Translation
AI总结：
提出新型自回归框架EarthMapper，通过地理坐标嵌入与多尺度特征对齐实现可控双向卫星图-地图翻译，并构建大规模数据集CNSatMap，在多项指标上超越现有方法且支持零样本任务。
摘要：
卫星影像和地图作为遥感中的两种基础数据模态，分别提供了对地球表面的直接观测和人类可解释的地理抽象。卫星图像与地图之间的双向翻译（BSMT）任务在城市规划和灾害响应应用中具有巨大潜力。然而，该任务面临两大主要挑战：首先，两种模态之间缺乏精确的像素级对齐，这使翻译过程变得极为复杂；其次，它需要同时实现地理特征的高级抽象和高质量的视觉合成，这进一步提升了技术复杂性。为了解决这些局限性，我们引入了EarthMapper，这是一种用于可控双向卫星图-地图翻译的新型自回归框架。EarthMapper采用地理坐标嵌入来锚定生成过程，确保了特定区域的适应性，并在地理条件联合尺度自回归（GJSA）过程中利用多尺度特征对齐，在单个训练周期内统一了双向翻译。引入了语义注入（SI）机制以增强特征级一致性，同时提出了关键点自适应引导（KPAG）机制，以在推理过程中动态平衡多样性与精度。我们进一步贡献了CNSatMap，这是一个包含38个中国城市302,132对精确对齐卫星-地图对的大规模数据集，能够实现稳健的基准测试。在CNSatMap和纽约数据集上的大量实验表明，EarthMapper具有卓越的性能，在视觉真实感、语义一致性和结构保真度方面均显著优于现有最先进的方法。此外，EarthMapper在图像修复、图像外绘和坐标条件生成等零样本任务中表现出色，凸显了其多功能性。
英文摘要：
Satellite imagery and maps, as two fundamental data modalities in remote sensing, offer direct observations of the Earth's surface and human-interpretable geographic abstractions, respectively. The task of bidirectional translation between satellite images and maps (BSMT) holds significant potential for applications in urban planning and disaster response. However, this task presents two major challenges: first, the absence of precise pixel-wise alignment between the two modalities substantially complicates the translation process; second, it requires achieving both high-level abstraction of geographic features and high-quality visual synthesis, which further elevates the technical complexity. To address these limitations, we introduce EarthMapper, a novel autoregressive framework for controllable bidirectional satellite-map translation. EarthMapper employs geographic coordinate embeddings to anchor generation, ensuring region-specific adaptability, and leverages multi-scale feature alignment within a geo-conditioned joint scale autoregression (GJSA) process to unify bidirectional translation in a single training cycle. A semantic infusion (SI) mechanism is introduced to enhance feature-level consistency, while a key point adaptive guidance (KPAG) mechanism is proposed to dynamically balance diversity and precision during inference. We further contribute CNSatMap, a large-scale dataset comprising 302,132 precisely aligned satellite-map pairs across 38 Chinese cities, enabling robust benchmarking. Extensive experiments on CNSatMap and the New York dataset demonstrate EarthMapper's superior performance, achieving significant improvements in visual realism, semantic consistency, and structural fidelity over state-of-the-art methods. Additionally, EarthMapper excels in zero-shot tasks like in-painting, out-painting and coordinate-conditional generation, underscoring its versatility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
