AI RESEARCH
Feed-Forward Gaussian Splatting from Sparse Aerial Views
arXiv CS.CV
•
ArXi:2605.19949v1 Announce Type: new Reconstructing large-scale urban scenes from sparse aerial views is a crucial yet challenging task. Due to biased top-down and shallow-oblique camera poses, sparse aerial captures exhibit strong evidence imbalance: roofs and open regions are repeatedly observed, while facades, distant buildings, and occluded structures receive little multi-view. Existing feed-forward 3D Gaussian Splatting methods directly regress a deterministic representation from sparse inputs, but this often leads to ghosting, melted facades, and stretched textures.