ViSA增强的空中视觉语言导航:一种增强视觉空间推理能力的空中视觉语言导航框架
ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation
AI总结:
ViSA增强框架通过结构化视觉提示提升空中VLN的空间推理能力,显著提高成功率,为该领域提供有力支持。
摘要:
现有的空中视觉语言导航(VLN)方法大多采用检测与规划流水线,将开放词汇检测转换为离散的文本场景图。这些方法受到空间推理能力不足和固有语言歧义的困扰。为了解决这些瓶颈,我们提出了一种增强视觉空间推理(ViSA)的空中VLN框架。具体而言,设计了一种三阶段协作架构,以利用结构化的视觉提示,使视觉语言模型(VLMs)能够在图像平面上直接进行推理,而无需额外训练或复杂的中间表示。在CityNav基准上的全面评估表明,ViSA增强的VLN在成功率上比完全训练的最先进(SOTA)方法提高了70.3%,阐明了其作为空中VLN系统骨干的巨大潜力。
英文摘要:
Existing aerial Vision-Language Navigation (VLN) methods predominantly adopt a detection-and-planning pipeline, which converts open-vocabulary detections into discrete textual scene graphs. These approaches are plagued by inadequate spatial reasoning capabilities and inherent linguistic ambiguities. To address these bottlenecks, we propose a Visual-Spatial Reasoning (ViSA) enhanced framework for aerial VLN. Specifically, a triple-phase collaborative architecture is designed to leverage structured visual prompting, enabling Vision-Language Models (VLMs) to perform direct reasoning on image planes without the need for additional training or complex intermediate representations. Comprehensive evaluations on the CityNav benchmark demonstrate that the ViSA-enhanced VLN achieves a 70.3\% improvement in success rate compared to the fully trained state-of-the-art (SOTA) method, elucidating its great potential as a backbone for aerial VLN systems.
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。