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

• URL: http://arxiv.org/abs/2605.14984v1
• Date: Thu, 14 May 2026 15:48:15 GMT
• Title: Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
• Abstract summary: We introduce Sat3DGen to address fundamental challenges, which embodies a geometry-first methodology.<n>This methodology enhances the feed-forward paradigm by integrating novel geometric constraints with a perspective-view training strategy.<n>For validation, we first constructed a new benchmark by pairing the VIGOR-OOD test set with high-resolution DSM data.
• Score: 41.808778998486666
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images [81.94999489820974]
  UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
  arXiv  Detail & Related papers  (2026-04-12T10:36:18Z)
• Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video [76.32954467706581]
  We propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams.<n>We use a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision.<n>Experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T09:53:21Z)
• Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations [18.442834011472005]
  A fundamental challenge in text-to-3D face generation is achieving high-quality geometry.<n>We introduce the Spherical Geometry Representation, a novel face representation that anchors geometric signals to uniform spherical coordinates.<n>We then introduce Spherical Diffusion Geometry, a conditional diffusion framework built upon this 2D map.
  arXiv  Detail & Related papers  (2026-01-19T20:15:45Z)
• GeoWorld: Unlocking the Potential of Geometry Models to Facilitate High-Fidelity 3D Scene Generation [68.02988074681427]
  Previous works leveraging video models for image-to-3D scene generation tend to suffer from geometric distortions and blurry content.<n>In this paper, we renovate the pipeline of image-to-3D scene generation by unlocking the potential of geometry models.<n>Our GeoWorld can generate high-fidelity 3D scenes from a single image and a given camera trajectory, outperforming prior methods both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2025-11-28T13:55:45Z)
• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification [59.17489431187807]
  We propose a framework that enhances 3D geometric fidelity by leveraging CLIP's hierarchical spatial semantics.<n>Our method significantly improves 3D few-shot class-incremental learning, achieving superior geometric coherence and robustness to texture bias.
  arXiv  Detail & Related papers  (2025-09-18T13:45:08Z)
• SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction [7.584417190255802]
  Monocular texture 3D human reconstruction aims to create a complete 3D digital avatar from just a single front-view human RGB image.<n>We propose a two-process 3D human reconstruction framework, SAT, which seamlessly learns various prior geometries in a unified manner.<n>We also propose an Online Animation Augmentation module to tackle data scarcity and improve reconstruction quality.
  arXiv  Detail & Related papers  (2025-08-27T08:52:35Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images [45.66479596827045]
  We propose a Geometry-enhanced NeRF (G-NeRF), which seeks to enhance the geometry priors by a geometry-guided multi-view synthesis approach. To tackle the absence of multi-view supervision for single-view images, we design the depth-aware training approach.
  arXiv  Detail & Related papers  (2024-04-11T04:58:18Z)
• Hybrid Approach for 3D Head Reconstruction: Using Neural Networks and Visual Geometry [3.970492757288025]
  We present a novel method for reconstructing 3D heads from a single or multiple image(s) using a hybrid approach based on deep learning and geometric techniques. We propose an encoder-decoder network based on the U-net architecture and trained on synthetic data only.
  arXiv  Detail & Related papers  (2021-04-28T11:31:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.