GeoViS：面向遥感视觉定位的地理空间奖励视觉搜索
GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding
把视觉定位从单步预测改成树结构逐步搜索+奖励引导的推理过程，这个「搜索-推理」范式可以直接迁移到小目标、大场景的开放词表定位任务上，尤其是需要多跳空间关系推理的场景。
原文依据 reformulates remote sensing visual grounding as a progressive search-and-reasoning process
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多模态大语言模型（MLLMs）的最新进展推动了视觉定位的显著进步，使文本查询与图像区域之间能够实现细粒度的跨模态对齐。然而，将此类能力迁移到遥感影像上仍然充满挑战，因为目标在公里级场景中往往极其微小，且查询通常涉及复杂的地理空间关系，例如相对位置、空间层级或远距离目标之间的上下文依赖。为应对这些挑战，我们提出 GeoViS，一个地理空间奖励视觉搜索框架，将遥感视觉定位重新表述为一个渐进式搜索与推理过程。GeoViS 不再单步直接预测目标位置，而是通过树结构的视觉线索序列主动探索全局图像，融合多模态感知、空间推理与奖励引导的探索，以迭代方式精化地理空间假设。该设计使模型能够检测细微的小尺度目标，同时保持对场景的整体感知。在五个遥感定位基准上的大量实验表明，GeoViS 实现了精确的地理空间理解，并在关键视觉定位指标上持续超越现有方法，凸显了其强大的跨域泛化能力与可解释性。
英文原文摘要 1396 字符
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.