Feed-Forward Gaussian Splatting from Sparse Aerial Views

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Dongli, Li, Zhuoxiao, Hua, Tongyan, Ren, Yinrui, Wei, Xiaobao, Qin, Rongjun, Zhao, Wufan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913146476691456
author Wu, Dongli
Li, Zhuoxiao
Hua, Tongyan
Ren, Yinrui
Wei, Xiaobao
Qin, Rongjun
Zhao, Wufan
author_facet Wu, Dongli
Li, Zhuoxiao
Hua, Tongyan
Ren, Yinrui
Wei, Xiaobao
Qin, Rongjun
Zhao, Wufan
contents 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 support. 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. Recent pseudo-view and video-based generative reconstruction methods use additional supervision or generative priors. However, they often lack a clear separation between observed geometry and prior-driven content, which can lead to plausible but inconsistent structures. We propose AnyCity, an observation-grounded generative reconstruction framework for sparse aerial urban scenes. AnyCity first predicts an observation-supported geometry latent to anchor reliable structures, and then uses scaffold-conditioned aerial completion tokens to predict a gated residual update for weakly constrained content before Gaussian decoding. During training, dense-to-sparse distillation transfers structural cues from dense-view reconstruction, while an aerial-adapted video diffusion prior provides fine-grained urban appearance cues through gated token conditioning. Observation-preserving objectives keep the refined representation consistent with input-supported geometry. At inference time, AnyCity reconstructs the final 3D Gaussian scene from sparse aerial views in a single feed-forward pass, achieving coherent urban novel-view synthesis with second-level inference. Experiments on synthetic, aerial-domain, UAV-textured, and real-world scenes show consistent improvements over feed-forward baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19949
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Feed-Forward Gaussian Splatting from Sparse Aerial Views
Wu, Dongli
Li, Zhuoxiao
Hua, Tongyan
Ren, Yinrui
Wei, Xiaobao
Qin, Rongjun
Zhao, Wufan
Computer Vision and Pattern Recognition
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 support. 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. Recent pseudo-view and video-based generative reconstruction methods use additional supervision or generative priors. However, they often lack a clear separation between observed geometry and prior-driven content, which can lead to plausible but inconsistent structures. We propose AnyCity, an observation-grounded generative reconstruction framework for sparse aerial urban scenes. AnyCity first predicts an observation-supported geometry latent to anchor reliable structures, and then uses scaffold-conditioned aerial completion tokens to predict a gated residual update for weakly constrained content before Gaussian decoding. During training, dense-to-sparse distillation transfers structural cues from dense-view reconstruction, while an aerial-adapted video diffusion prior provides fine-grained urban appearance cues through gated token conditioning. Observation-preserving objectives keep the refined representation consistent with input-supported geometry. At inference time, AnyCity reconstructs the final 3D Gaussian scene from sparse aerial views in a single feed-forward pass, achieving coherent urban novel-view synthesis with second-level inference. Experiments on synthetic, aerial-domain, UAV-textured, and real-world scenes show consistent improvements over feed-forward baselines.
title Feed-Forward Gaussian Splatting from Sparse Aerial Views
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.19949