GeoViS: 基于地理奖励的视觉搜索用于遥感视觉定位
GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding
AI总结：
GeoViS通过地理奖励机制，实现了遥感影像中的细粒度视觉定位，通过逐步搜索和推理提升小目标检测精度与跨领域泛化能力。
摘要：
近年来，多模态大语言模型（MLLMs）的进展在视觉定位领域取得了显著进展，使文本查询与图像区域之间的细粒度跨模态对齐成为可能。然而，将这些能力转移到遥感影像中仍然具有挑战性，因为目标通常在千米级场景中非常微小，且查询通常涉及复杂的地理空间关系，如相对位置、空间层次或跨远距离物体的上下文依赖性。为了解决这些挑战，我们提出了GeoViS，一种基于地理奖励的视觉搜索框架，将遥感视觉定位重新表述为一个逐步搜索和推理过程。与其在单步中直接预测目标位置不同，GeoViS通过树状结构的视觉线索序列主动探索整个图像，整合多模态感知、空间推理和奖励引导的探索，以迭代方式完善地理空间假设。这种设计使模型能够检测细微的小尺度目标，同时保持整体场景意识。在五个遥感定位基准上的广泛实验表明，GeoViS实现了精确的地理空间理解，并在关键的视觉定位指标上持续超越现有方法，突显了其强大的跨领域泛化能力和可解释性。
英文摘要：
Recent advances in multimodal large language models(MLLMs) have led to remarkable progress in visual grounding, enabling fine-grained cross-modal alignment between textual queries and image regions. However, transferring such capabilities to remote sensing imagery remains challenging, as targets are often extremely small within kilometer-scale scenes, and queries typically involve intricate geospatial relations such as relative positions, spatial hierarchies, or contextual dependencies across distant objects. To address these challenges, we propose GeoViS, a Geospatially Rewarded Visual Search framework that reformulates remote sensing visual grounding as a progressive search-and-reasoning process. Rather than directly predicting the target location in a single step, GeoViS actively explores the global image through a tree-structured sequence of visual cues, integrating multimodal perception, spatial reasoning, and reward-guided exploration to refine geospatial hypotheses iteratively. This design enables the model to detect subtle small-scale targets while maintaining holistic scene awareness. Extensive experiments on five remote sensing grounding benchmarks demonstrate that GeoViS achieves precise geospatial understanding and consistently surpasses existing methods across key visual grounding metrics, highlighting its strong cross-domain generalization and interpretability.
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。
