jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
This tool helps urban planners, architects, or game developers create detailed, immersive 3D models of urban environments. It takes readily available satellite imagery and other 2D data as input and produces geometrically accurate and photorealistic 3D urban scenes. These models can then be explored in real-time, making it useful for visualization and simulation.
762 stars. Actively maintained with 3 commits in the last 30 days.
Use this if you need to generate high-quality, explorable 3D models of large urban areas from existing satellite images, without the need for expensive 3D scanning.
Not ideal if you require highly precise, sub-meter level interior building details or real-time object tracking within the 3D scene.
Stars
762
Forks
77
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jayin92/Skyfall-GS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...
aminshabani/house_diffusion
The implementation of "HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with...