Local Ai
G3AR: Graph-Guided Neural Visual Geometry for Scalable Multi-Sequence Aerial Registration
arXiv:2609.16603v1 Announce Type: new Abstract: Full-context neural visual geometry is impractical for thousands of images, while sequence-based chunking poorly captures irregular non-local overlap in
arXiv:2609.16603v1 Announce Type: new 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.
Related
- Geometry-aided Vision-based Localization of Future Mars Helicopters in Challenging Illumination Conditions
- Multi-Submap Implicit Neural SLAM with Local-to-Global Loop Closure for Large-Scale Scene Reconstruction
- GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly
Source: arXiv cs.CV | 2026-09-16