G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
Published 17 Sept 2026arXiv:2609.16603
Updated 25 h ago · first seen 16 Sept 2026
paper_01M2MD9PSMDX4PDY47ME8G8MYS
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.
Organizations
Organizations 0
No organization stated. arXiv metadata does not carry affiliations; an organization is linked only when a model card or lab page cites the paper.
Models
Models introduced or described 0
Inbound described_by relations from model cards and documentation.
No model links this paper yet
Datasets
Datasets used 0
No dataset relation recorded.
Benchmarks
Benchmarks used 0
No benchmark relation recorded.
Code
Repositories & frameworks 0
No repository linked.
Timeline
Timeline 2
- Property changedPaperG3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration: published at changed from 2026-09-16T04:00:00+00:00 to 2026-09-17T04:00:00+00:00
Published16 Sept 2026→17 Sept 2026arxiv - New paperPaperG3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
New paper: G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
arxiv
Sources
Sources 1
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.