Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Jie-Ying, Liu, Yi-Ruei, Tsai, Shr-Ruei, Chang, Wei-Cheng, Wu, Chung-Ho, Chan, Jiewen, Zhao, Zhenjun, Lin, Chieh Hubert, Liu, Yu-Lun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914403686809600
author Lee, Jie-Ying
Liu, Yi-Ruei
Tsai, Shr-Ruei
Chang, Wei-Cheng
Wu, Chung-Ho
Chan, Jiewen
Zhao, Zhenjun
Lin, Chieh Hubert
Liu, Yu-Lun
author_facet Lee, Jie-Ying
Liu, Yi-Ruei
Tsai, Shr-Ruei
Chang, Wei-Cheng
Wu, Chung-Ho
Chan, Jiewen
Zhao, Zhenjun
Lin, Chieh Hubert
Liu, Yu-Lun
contents Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task for immersive and embodied applications. The challenge lies in the lack of large-scale and high-quality real-world 3D scans for training generalizable generative models. In this paper, we take an alternative route to create large-scale 3D scenes by leveraging readily available satellite imagery for realistic coarse geometry and open-domain diffusion models for high-quality close-up appearance synthesis. We propose Skyfall-GS, a novel 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, and also featuring real-time, immersive 3D exploration. We tailor a curriculum-driven iterative refinement strategy to progressively enhance geometric completeness and photorealistic texture. Extensive experiments demonstrate that Skyfall-GS provides improved cross-view consistent geometry and more realistic textures compared to state-of-the-art approaches. Project page: https://skyfall-gs.jayinnn.dev/
format Preprint
id arxiv_https___arxiv_org_abs_2510_15869
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Lee, Jie-Ying
Liu, Yi-Ruei
Tsai, Shr-Ruei
Chang, Wei-Cheng
Wu, Chung-Ho
Chan, Jiewen
Zhao, Zhenjun
Lin, Chieh Hubert
Liu, Yu-Lun
Computer Vision and Pattern Recognition
Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task for immersive and embodied applications. The challenge lies in the lack of large-scale and high-quality real-world 3D scans for training generalizable generative models. In this paper, we take an alternative route to create large-scale 3D scenes by leveraging readily available satellite imagery for realistic coarse geometry and open-domain diffusion models for high-quality close-up appearance synthesis. We propose Skyfall-GS, a novel 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, and also featuring real-time, immersive 3D exploration. We tailor a curriculum-driven iterative refinement strategy to progressively enhance geometric completeness and photorealistic texture. Extensive experiments demonstrate that Skyfall-GS provides improved cross-view consistent geometry and more realistic textures compared to state-of-the-art approaches. Project page: https://skyfall-gs.jayinnn.dev/
title Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.15869