Scene Grounding In the Wild

• URL: http://arxiv.org/abs/2603.26584v2
• Date: Fri, 03 Apr 2026 09:55:45 GMT
• Title: Scene Grounding In the Wild
• Abstract summary: Reconstructing accurate 3D models of large-scale real-world scenes from unstructured, in-the-wild imagery remains a core challenge in computer vision.<n>We propose a framework that grounds each partial reconstruction to a complete reference model of the scene.<n>We demonstrate that our approach consistently improves global alignment when with various classical and learning-based pipelines.
• Score: 27.597534811067348
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reconstructing accurate 3D models of large-scale real-world scenes from unstructured, in-the-wild imagery remains a core challenge in computer vision, especially when the input views have little or no overlap. In such cases, existing reconstruction pipelines often produce multiple disconnected partial reconstructions or erroneously merge non-overlapping regions into overlapping geometry. In this work, we propose a framework that grounds each partial reconstruction to a complete reference model of the scene, enabling globally consistent alignment even in the absence of visual overlap. We obtain reference models from dense, geospatially accurate pseudo-synthetic renderings derived from Google Earth Studio. These renderings provide full scene coverage but differ substantially in appearance from real-world photographs. Our key insight is that, despite this significant domain gap, both domains share the same underlying scene semantics. We represent the reference model using 3D Gaussian Splatting, augmenting each Gaussian with semantic features, and formulate alignment as an inverse feature-based optimization scheme that estimates a global 6DoF pose and scale while keeping the reference model fixed. Furthermore, we introduce the WikiEarth dataset, which registers existing partial 3D reconstructions with pseudo-synthetic reference models. We demonstrate that our approach consistently improves global alignment when initialized with various classical and learning-based pipelines, while mitigating failure modes of state-of-the-art end-to-end models.

Related papers

• GenRec: Knowing Where to Reconstruct and Where to Generate [106.48347271421765]
  GenRec is a flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow.<n>It attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones.
  arXiv  Detail & Related papers  (2026-08-18T14:31:19Z)
• Glob3R: Global Structure-from-Motion with 3D Foundation Models [44.33296410481359]
  Glob3R is a global SfM-style reconstruction built on 3D foundation models.<n>Our key idea is to explicitly optimize feed-forward geometric predictions.<n>Experiments on indoor, outdoor, large-scale driving, and unordered SfM benchmarks demonstrate that Glob3R achieves robust and accurate reconstruction.
  arXiv  Detail & Related papers  (2026-07-10T09:18:35Z)
• Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views [0.8435195043404353]
  We introduce Generative Reconstruction from Disjoint Views as a new paradigm.<n>We propose GLADOS, a general, modular framework that operates through three stages.<n>As an architectureagnostic framework, GLADOS enables seamless integration of future advances in generation, reconstruction, and inpainting.
  arXiv  Detail & Related papers  (2026-05-08T10:24:23Z)
• RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations [70.83499963694238]
  RnG (Reconstruction and Generation) is a novel feed-forward Transformer that unifies reconstruction and generation.<n>It reconstructs visible geometry and generates plausible, coherent unseen geometry and appearance.<n>Our method achieves state-of-the-art performance in both generalizable 3D reconstruction and novel view generation.
  arXiv  Detail & Related papers  (2026-03-01T17:25:32Z)
• TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction [57.46712611558817]
  3D vision foundation models have shown strong generalization in reconstructing key 3D attributes from uncalibrated images through a single feed-forward pass.<n>Recent strategies align consecutive predictions by solving global transformation, yet our analysis reveals their fundamental limitations in assumption validity, local alignment scope, and robustness under noisy geometry.<n>We propose a higher-DOF and long-term alignment framework based on Thin Plate Spline, leveraging globally propagated control points to correct spatially varying inconsistencies.
  arXiv  Detail & Related papers  (2025-12-02T02:22:20Z)
• OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting [78.70702961852119]
  OracleGS reconciles generative completeness with regressive fidelity for sparse view Gaussian Splatting.<n>Our approach conditions the powerful generative prior on multi-view geometric evidence, filtering hallucinatory artifacts while preserving plausible completions in under-constrained regions.
  arXiv  Detail & Related papers  (2025-09-27T11:19:32Z)
• DSG-World: Learning a 3D Gaussian World Model from Dual State Videos [14.213608866611784]
  We present DSG-World, a novel end-to-end framework that explicitly constructs a 3D Gaussian World model from Dual State observations.<n>Our approach builds dual segmentation-aware Gaussian fields and enforces bidirectional photometric and semantic consistency.
  arXiv  Detail & Related papers  (2025-06-05T16:33:32Z)
• GenS: Generalizable Neural Surface Reconstruction from Multi-View Images [20.184657468900852]
  GenS is an end-to-end generalizable neural surface reconstruction model. Our representation is more powerful, which can recover high-frequency details while maintaining global smoothness. Experiments on popular benchmarks show that our model can generalize well to new scenes.
  arXiv  Detail & Related papers  (2024-06-04T17:13:10Z)
• Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversion [54.151979979158085]
  We introduce a principled end-to-end reconstruction framework for natural images, where accurate ground-truth poses are not available. We leverage an unconditional 3D-aware generator, to which we apply a hybrid inversion scheme where a model produces a first guess of the solution. Our framework can de-render an image in as few as 10 steps, enabling its use in practical scenarios.
  arXiv  Detail & Related papers  (2022-11-21T17:42:42Z)
• Single-view 3D Mesh Reconstruction for Seen and Unseen Categories [69.29406107513621]
  Single-view 3D Mesh Reconstruction is a fundamental computer vision task that aims at recovering 3D shapes from single-view RGB images. This paper tackles Single-view 3D Mesh Reconstruction, to study the model generalization on unseen categories. We propose an end-to-end two-stage network, GenMesh, to break the category boundaries in reconstruction.
  arXiv  Detail & Related papers  (2022-08-04T14:13:35Z)
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [86.77318031029404]
  We propose a framework that performs scene reconstruction and semantic scene completion jointly in an incremental and real-time manner. Our framework relies on a novel neural architecture designed to process occupancy maps and leverages voxel states to accurately and efficiently fuse semantic completion with the 3D global model.
  arXiv  Detail & Related papers  (2020-10-26T15:31:52Z)
• SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images [49.52782544649703]
  We propose a novel approach to reconstruct 3D human body shapes based on a sparse set of RGBD frames. The main challenge is how to robustly fuse these sparse frames into a canonical 3D model. Our framework is flexible, with potential applications going beyond shape reconstruction.
  arXiv  Detail & Related papers  (2020-06-05T18:53:36Z)

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.