SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors

TL;DR

SatSkylines is a novel method for generating detailed 3D building models from satellite images using coarse geometric priors, supported by a large-scale dataset, achieving accurate and flexible results.

Contribution

The paper introduces a new approach that transforms coarse priors into detailed 3D buildings from satellite imagery, with a large dataset to support this task.

Findings

Effective 3D building generation from satellite images.

Strong generalization demonstrated across diverse datasets.

Large-scale dataset of 50,000 stylized building assets.

Abstract

We present SatSkylines, a 3D building generation approach that takes satellite imagery and coarse geometric priors. Without proper geometric guidance, existing image-based 3D generation methods struggle to recover accurate building structures from the top-down views of satellite images alone. On the other hand, 3D detailization methods tend to rely heavily on highly detailed voxel inputs and fail to produce satisfying results from simple priors such as cuboids. To address these issues, our key idea is to model the transformation from interpolated noisy coarse priors to detailed geometries, enabling flexible geometric control without additional computational cost. We have further developed Skylines-50K, a large-scale dataset of over 50,000 unique and stylized 3D building assets in order to support the generations of detailed building models. Extensive evaluations indicate the effectiveness of our model and strong generalization ability.