G3AR：面向可扩展多序列航空配准的图引导神经视觉几何
G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
浏览论文内容
中文总结 AI 辅助
G3AR提出图引导框架，通过几何验证的图像邻近图构建有界重叠分块，利用最大生成树定义拓扑，实现可扩展的多序列航空配准，在四个真实场景中提升位姿精度并降低运行时间。
中文摘要 AI 辅助
全上下文神经视觉几何对于数千张图像而言不切实际，而基于序列的分块方法难以捕捉多序列航空采集中的不规则非局部重叠。我们提出用于航空配准的图引导神经视觉几何（G3AR），一个用于可扩展密集神经几何的图引导框架。在局部推理之前，G3AR构建一个经过几何验证的图像邻近图，该图引导有界重叠分块，并生成一个分块图，其最大生成树定义对齐拓扑。兼容的骨干网络独立处理分块；共享图像预测随后估计三维相似性（Sim(3)）变换，以在公共坐标系中配准局部相机和几何。在四个真实航空场景中，G3AR在匹配的VGGT和Pi3骨干比较中改善了位姿误差和运行时间，而其DA3变体在评估的神经几何方法中实现了最低的位姿误差。
英文摘要
Full-context neural visual geometry is impractical for thousands of images, while sequence-based chunking poorly captures irregular non-local overlap in multi-sequence aerial collections. We present Graph-Guided Neural Visual Geometry for Aerial Registration (G3AR), a graph-guided framework for scalable dense neural geometry. Before local inference, G3AR builds a geometrically verified image-proximity graph that guides bounded overlapping chunks and induces a chunk graph whose maximum spanning tree defines alignment topology. Compatible backbones process chunks independently; shared-image predictions then estimate three-dimensional similarity (Sim(3)) transforms that register local cameras and geometry in a common frame. Across four real aerial scenes, G3AR improves pose error and runtime in matched VGGT- and Pi3-backed comparisons, while its DA3 variant achieves the lowest pose error among evaluated neural-geometry methods.
发表机构
- National Tsing Hua University（国立清华大学）
- NVIDIA（英伟达）
机构由 AI 辅助整理，请以论文原文为准。
