G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration

2026-09-14

AI Summary

本文提出G3AR方法，通过构建几何验证的图像邻近图指导分块处理，解决大规模航拍图像序列注册问题，提高了姿态误差和运行时间。

Abstract

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.

Problem

• neural visual geometry
• multi-sequence aerial registration
• image-proximity graph
• chunking
• alignment topology

Innovation

• Graph-Guided
• Neural Visual Geometry
• Aerial Registration
• Sim(3) Transforms
• Chunk Graph