看见我们看不见的：恶劣对地观测条件下目标计数的地理引导推理基准
See What We Cannot See: A Geo-guided Reasoning Benchmark for Object Counting under Adverse Earth Observation Conditions
把土地利用图、地图等地理模态作为外观失效时的稳定结构先验，为遥感视觉任务提供了一条不依赖可见光外观的推理路径；其数据引擎（多地理模态对齐、真实退化模拟、点标注）可直接复用于构建恶劣条件下的计数与定位基准。
原文依据 earth observation inherently provides complementary geo-modalities, including land use and map, which offer stable structural and contextual priors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当视觉线索被云、雾、阴影或低光照条件遮蔽时，遥感图像中的目标计数变得极具挑战。然而，对地观测本身提供了互补的地理模态，包括土地利用图和地图，它们提供了稳定的结构与上下文先验，在外观线索失效时依然可用。本文提出 GROC，这是首个面向恶劣对地观测条件下目标计数的大规模地理引导推理数据集。GROC 包含 14K 幅图像上的 120 万个点标注，每幅图像均与保留原始地理空间信息的 3 种模态对齐。我们还提供了一个数据引擎，用于采集具有多地理模态、真实退化与可靠标注的大规模目标计数数据集。我们进一步提出一个计数智能体，能够自适应地利用地理模态给出可靠估计。大量实验表明，现有模型难以“看穿”恶劣条件，而地理模态提升了鲁棒性。GROC 建立了首个显式挑战模型去看见其无法看见之物的基准，为对地观测中的地理引导非模态推理开辟了新方向。
英文原文摘要 1213 字符
Object counting in remote sensing imagery becomes challenging when visual cues are obscured by clouds, fog, shadows, or low-light conditions. Yet earth observation inherently provides complementary geo-modalities, including land use and map, which offer stable structural and contextual priors that remain available when appearance cues fail. In this paper, we introduce GROC, the first large-scale dataset Geo-guided Reasoning in Object Counting under adverse earth observation conditions. GROC contains 1.2 million point annotations over 14K images, each aligned with 3 modalities that preserve original geospatial information. We also provide a data engine to collect a large-scale object counting dataset with multiple geo-modalities, realistic degradations, and reliable annotations. We further present an counting agent that adaptively leverages geo-modalities to produce reliable estimates. Extensive experiments show that existing models struggle to "see" through adverse conditions, whereas geo-modalities improve robustness. GROC establishes the first benchmark that explicitly challenges models to see what they cannot see, charting a new direction for geo-guided amodal reasoning in earth observation.