TL;DR
This paper introduces a novel method for city-scale 3D reconstruction from satellite images, using a 2.5D height map and generative texture restoration to synthesize realistic ground views from extreme off-nadir satellite imagery.
Contribution
It proposes a specialized city geometry model and a texture enhancement pipeline tailored for satellite inputs, enabling robust, high-fidelity urban reconstructions from sparse, degraded images.
Findings
Reconstructed a 4 km² urban area from few satellite images.
Achieved state-of-the-art photorealistic ground view synthesis.
Produced watertight meshes with crisp roofs and extruded facades.
Abstract
City-scale 3D reconstruction from satellite imagery presents the challenge of extreme viewpoint extrapolation, where our goal is to synthesize ground-level novel views from sparse orbital images with minimal parallax. This requires inferring nearly viewpoint gaps from image sources with severely foreshortened facades and flawed textures, causing state-of-the-art reconstruction engines such as NeRF and 3DGS to fail. To address this problem, we propose two design choices tailored for city structures and satellite inputs. First, we model city geometry as a 2.5D height map, implemented as a Z-monotonic signed distance field (SDF) that matches urban building layouts from top-down viewpoints. This stabilizes geometry optimization under sparse, off-nadir satellite views and yields a watertight mesh with crisp roofs and clean, vertically extruded facades. Second, we paint the mesh…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
