Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image

Ming Qian, Zimin Xia, Changkun Liu, Shuailei Ma, Wen Wang, Zeran Ke, Bin Tan, Hang Zhang, Gui-Song Xia

arXiv:2605.14984 · 2026-05-13 공개 · arXiv · PDF

vision-language scene-generation photorealism dsm-estimation semantic-maps meshing satellite-to-street geometry-first

Abstract

Generating a street-level 3D scene from a single satellite image is a crucial yet challenging task. Current methods present a stark trade-off: geometry-colorization models achieve high geometric fidelity but are typically building-focused and lack semantic diversity. In contrast, proxy-based models use feed-forward image-to-3D frameworks to generate holistic scenes by jointly learning geometry and texture, a process that yields rich content but coarse and unstable geometry. We attribute these geometric failures to the extreme viewpoint gap and sparse, inconsistent supervision inherent in satellite-to-street data. We introduce Sat3DGen to address these fundamental challenges, which embodies a geometry-first methodology. This methodology enhances the feed-forward paradigm by integrating novel geometric constraints with a perspective-view training strategy, explicitly countering the primary sources of geometric error. This geometry-centric strategy yields a dramatic leap in both 3D accuracy and photorealism. For validation, we first constructed a new benchmark by pairing the VIGOR-OOD test set with high-resolution DSM data. On this benchmark, our method improves geometric RMSE from 6.76m to 5.20m. Crucially, this geometric leap also boosts photorealism, reducing the Fréchet Inception Distance (FID) from $\sim$40 to 19 against the leading method, Sat2Density++, despite using no extra tailored image-quality modules. We demonstrate the versatility of our high-quality 3D assets through diverse downstream applications, including semantic-map-to-3D synthesis, multi-camera video generation, large-scale meshing, and unsupervised single-image Digital Surface Model (DSM) estimation. The code has been released on https://github.com/qianmingduowan/Sat3DGen.

한국어 요약

📋 한 줄 요약

**[3D 생성 / 위성-스트리트 합성]** 단일 위성 영상으로부터 holistic한 거리 수준 3D 장면을 생성하는 geometry-first feed-forward 프레임워크 Sat3DGen 제안.

🎯 핵심 기여도

💡 핵심 아이디어

위성→거리 변환에서 사실성(photorealism)은 기하 정확도가 안정적일 때 자연스럽게 따라온다는 관점. 별도의 이미지 품질 모듈을 추가하는 대신, 기하 학습을 먼저 안정화하면 FID까지 동반 개선된다는 통찰.

🔬 기술적 접근법

📊 주요 결과

💭 의의 및 한계

**의의**: 위성→거리 3D 생성에서 기하 우선 설계의 효과를 명시적으로 보이고 응용 다양성을 한 모델로 증명. **한계**: VIGOR-OOD 중심 평가로 도시·자연 환경 다양성에 대한 일반화는 후속 검증 필요.

🚀 실용적 활용