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

Hugging Face Daily Papers Papers
3d-generation satellite-imagery scene-generation geometry-first computer-vision 3d-from-single-image generative-model

Summary

Sat3DGen introduces a geometry-first approach for generating street-level 3D scenes from a single satellite image, achieving improved geometric accuracy and photorealism through novel constraints and training strategies. The method demonstrates significant improvements over prior work on the VIGOR-OOD benchmark.

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 sim40 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.
Original Article
View Cached Full Text

Cached at: 05/15/26, 04:26 PM

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

Source: https://huggingface.co/papers/2605.14984

Abstract

Sat3DGen addresses the challenge of generating street-level 3D scenes from satellite images by employing a geometry-first approach that improves both geometric accuracy and photorealism through novel constraints and training strategies.

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 usefeed-forward image-to-3D frameworksto 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 ageometry-first methodology. This methodology enhances the feed-forward paradigm by integrating novelgeometric constraintswith aperspective-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 theVIGOR-OODtest set withhigh-resolution DSMdata. On this benchmark, our method improves geometric RMSE from 6.76m to 5.20m. Crucially, this geometric leap also boosts photorealism, reducing theFréchet Inception Distance(FID) from sim40 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-imageDigital Surface Model(DSM) estimation. The code has been released on https://github.com/qianmingduowan/Sat3DGen.

View arXiv pageView PDFProject pageGitHub28Add to collection

Get this paper in your agent:

hf papers read 2605\.14984

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### qian43/Sat3DGen Image-to-3D• Updatedabout 1 hour ago • 44 • 2

Datasets citing this paper1

#### qian43/VIGOR_SAT3DGEN_add_skymask_DSM_satdepth Viewer• Updatedabout 1 hour ago • 89.9k • 51 • 2

Spaces citing this paper1

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

ABot-Earth 0.5: Generative 3D Earth Model

Hugging Face Daily Papers

ABot-Earth 0.5 is a generative 3D framework that synthesizes realistic 3D urban environments from satellite imagery using 3D Gaussian Splatting, enabling real-time visualization and closed-loop UAV navigation at low cost.

SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

Hugging Face Daily Papers

SynCity 3000 introduces a framework for generating large, globally coherent 3D scenes by adapting image-to-3D generators as convolutional operators, fine-tuned on synthetic scene data from a new data engine.

Pixal3D: Pixel-Aligned 3D Generation from Images

Hugging Face Daily Papers

Pixal3D introduces a pixel-aligned 3D generation approach that improves fidelity by establishing direct pixel-to-3D correspondences through back-projection conditioning, addressing issues in canonical space generation.