GSplatVNM：利用 Gaussian Splatting 为视觉导航模型进行视点合成
GSplatVNM: Point-of-View Synthesis for Visual Navigation Models Using Gaussian Splatting
AI总结：
本文提出 GSplatVNM，将 3DGS 与视觉导航模型结合，通过合成中间视点弥补稀疏图像数据库间隙并降低存储开销，实验证明其提升导航效率且对不同稀疏度具有鲁棒性。
摘要：
本文提出了一种将 3D Gaussian Splatting（3DGS）与视觉导航模型（Visual Navigation Models，VNMs）相结合的图像目标导航新方法，我们将其称为 GSplatVNM。VNMs 通过一系列视点图像引导机器人，且无需度量定位或针对特定环境的训练，因此为图像目标导航提供了一种富有前景的范式。然而，尤其是在可用图像数据库较为稀疏时，如何从起点到目标构建稠密且可通行的目标视点序列，仍是一个核心挑战。为应对这些挑战，我们提出了一种基于 3DGS、面向 VNMs 的视点合成框架。该框架通过合成中间视点，无缝弥补稀疏数据中的间隙，同时显著降低存储开销。在照片级真实感模拟器中的实验结果表明，我们的方法不仅提高了导航效率，而且在图像数据库稀疏程度不断变化的情况下表现出鲁棒性。
英文摘要：
This paper presents a novel approach to image-goal navigation by integrating 3D Gaussian Splatting (3DGS) with Visual Navigation Models (VNMs), a method we refer to as GSplatVNM. VNMs offer a promising paradigm for image-goal navigation by guiding a robot through a sequence of point-of-view images without requiring metrical localization or environment-specific training. However, constructing a dense and traversable sequence of target viewpoints from start to goal remains a central challenge, particularly when the available image database is sparse. To address these challenges, we propose a 3DGS-based viewpoint synthesis framework for VNMs that synthesizes intermediate viewpoints to seamlessly bridge gaps in sparse data while significantly reducing storage overhead. Experimental results in a photorealistic simulator demonstrate that our approach not only enhances navigation efficiency but also exhibits robustness under varying levels of image database sparsity.
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。
