The evaluation videos for Skyfall-GS

This repository contains the evaluation videos for the paper Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery.

Project Page | GitHub | arXiv

Skyfall-GS is a hybrid framework that synthesizes immersive city-block scale 3D urban scenes by combining satellite reconstruction with diffusion refinement, eliminating the need for costly 3D annotations. It features real-time, immersive 3D exploration and a curriculum-driven iterative refinement strategy to enhance geometric completeness and photorealistic textures.

Citation

If you find this work useful, please consider citing:

@article{lee2025SkyfallGS,
  title = {{Skyfall-GS}: Synthesizing Immersive {3D} Urban Scenes from Satellite Imagery},
  author = {Jie-Ying Lee and Yi-Ruei Liu and Shr-Ruei Tsai and Wei-Cheng Chang and Chung-Ho Wu and Jiewen Chan and Zhenjun Zhao and Chieh Hubert Lin and Yu-Lun Liu},
  journal = {arXiv preprint},
  year = {2025},
  eprint = {2510.15869},
  archivePrefix = {arXiv}
}