Summary
This work looks at how to improve detailed 3D maps made from aerial photos by adding new images taken from the ground, even when the exact camera locations are unknown. The researchers created a method called SkyAnchor, which uses the existing aerial 3D model as a stable reference to figure out where the new ground pictures fit. It first finds a few well-matched points between aerial and ground views, then builds the full position path for the ground images by connecting these points, updating the model to include more realistic street-level details. Tests showed this method produces accurate positions and high-quality 3D scenes from both above and street views.
What this means in practice
- •For urban planners: Update aerial 3D city models with fresh street-level imagery when camera locations are uncertain, improving detailed maps for planning and visualization.
- •For augmented reality developers: Integrate unposed ground-level images into existing aerial 3D scenes to create more immersive AR environments with accurate spatial alignment.
Authors
Zhuoxiao Li, Xinyi Liu, Taoyu Wu, Yinrui Ren, Tongyan Hua, Ou Jing, Shuai Zhang, Dongli Wu, Rongjun Qin, Ge Lin Kan, Wufan Zhao
Abstract
We study how to update a pre-built aerial scene with a newly captured, unposed ground-view sequence. The aerial scene already contains a reliable metric Structure-from-Motion (SfM) reconstruction and a pre-trained 3D Gaussian Splatting (3DGS) model, whereas the ground-view sequence is collected later to add street-level appearance but has unknown camera poses and global scale. Registering this sequence to the aerial SfM reconstruction is challenging because single-image cross-view localization is brittle and long trajectories are prone to drift. To address these challenges, we present SkyAnchor, which treats the existing aerial scene as a fixed scaffold for ground-view registration and scene update instead of jointly reconstructing aerial and ground imagery from scratch. It first localizes short groups of consecutive ground frames against geometrically verified aerial support, producing sparse anchor poses. It then recovers the full ground trajectory with anchor-constrained submaps, fixing the front and rear anchor poses during incremental registration and bundle adjustment. Finally, it inserts filtered ground Gaussians while preserving the aerial view, followed by lightweight joint refinement. Experiments on seven real aerial--ground scenes show accurate metric ground trajectories and updated 3D Gaussian scenes with strong aerial- and ground-view rendering quality.