用卫星图和粗略几何先验生成逼真3D建筑，灵活可控且高效。
SAT-SKYLINES: 3D Building Generation from Satellite Imagery and Coarse Geometric Priors
- 通过建模从粗糙先验到细节几何的转换过程，实现灵活控制。
- 在5万+建筑数据集上训练，生成效果显著优于传统方法。
- 适合城市建模、游戏开发等需要快速生成3D建筑的场景。
我们提出SatSkylines，一种基于卫星图像与粗略几何先验的3D建筑生成方法。现有基于图像的3D生成方法仅依赖卫星图像的俯视图时，难以准确恢复建筑结构；而传统的3D细节化方法则过度依赖高精度体素输入，在简单先验（如立方体）下表现不佳。为此，我们的核心思路是建模从插值后的噪声粗略先验到详细几何的变换过程，实现无需额外计算成本的灵活几何控制。我们进一步构建了Skylines-50K，一个包含超过5万组独特且风格化的3D建筑资产的大规模数据集，以支持高质量建筑模型的生成。大量评估表明，该模型有效且具备强大的泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。