cs.CVSep 15, 2026

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

Authors: Jeng Wen Joshua LeanTing-Yu YenWei-Fang SunSimon SeeHung-Kuo ChuShih-Hsuan Hung

Organizations: National Tsing Hua University Hsinchu, Taiwan · NVIDIA AI Technology Center Taiwan · NVIDIA AI Technology Center Singapore

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.

Explore similar work

CardsList