LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment

• URL: http://arxiv.org/abs/2603.19609v2
• Date: Tue, 24 Mar 2026 12:24:58 GMT
• Title: LoD-Loc v3: Generalized Aerial Localization in Dense Cities using Instance Silhouette Alignment
• Abstract summary: We present LoD-Loc v3, a novel method for generalized aerial visual localization in dense urban environments.<n>We develop a new synthetic data generation pipeline that produces InsLoD-Loc - the largest instance segmentation dataset for aerial imagery to date.<n>We reformulate the localization paradigm by shifting from semantic to instance silhouette alignment, which significantly reduces pose estimation ambiguity in dense scenes.
• Score: 27.863242898871963
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present LoD-Loc v3, a novel method for generalized aerial visual localization in dense urban environments. While prior work LoD-Loc v2 achieves localization through semantic building silhouette alignment with low-detail city models, it suffers from two key limitations: poor cross-scene generalization and frequent failure in dense building scenes. Our method addresses these challenges through two key innovations. First, we develop a new synthetic data generation pipeline that produces InsLoD-Loc - the largest instance segmentation dataset for aerial imagery to date, comprising 100k images with precise instance building annotations. This enables trained models to exhibit remarkable zero-shot generalization capability. Second, we reformulate the localization paradigm by shifting from semantic to instance silhouette alignment, which significantly reduces pose estimation ambiguity in dense scenes. Extensive experiments demonstrate that LoD-Loc v3 outperforms existing state-of-the-art (SOTA) baselines, achieving superior performance in both cross-scene and dense urban scenarios with a large margin. The project is available at https://nudt-sawlab.github.io/LoD-Locv3/.

Related papers

• SemCityLoc: Aerial 6DoF Localization Using Semantic 3D City Models [51.121529170856064]
  We propose SemCityLoc, a semantic-geometric alignment system that reframes aerial pose estimation.<n>Instead of matching sparse contours or dense texture, our method aligns semantic surfaces and monocular depth with lightweight semantic 3D building models.<n>Experiments demonstrate substantial improvements over existing map-based approaches.
  arXiv  Detail & Related papers  (2026-06-25T18:13:39Z)
• FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation [75.74617373156902]
  FreeScale is a framework that transforms limited real-world image sequences into a scalable source of high-quality training data.<n>We show FreeScale's effectiveness by scaling up the training of feedforward NVS models, achieving a notable gain of 2.7 dB in PSNR.<n>Our work provides a practical and powerful data generation engine to overcome a fundamental bottleneck in 3D vision.
  arXiv  Detail & Related papers  (2026-04-12T08:00:53Z)
• Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion [18.943643720564996]
  Sat2City is a novel framework that synergizes the representational capacity of sparse voxel grids with latent diffusion models.<n>We introduce a dataset of synthesized large-scale 3D cities paired with satellite-view height maps.<n>Our framework generates detailed 3D structures from a single satellite image, achieving superior fidelity compared to existing city generation models.
  arXiv  Detail & Related papers  (2025-07-06T14:30:08Z)
• LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment [16.133812789068806]
  We propose a novel method for aerial visual localization over low Level-of-Detail (LoD) city models.<n>LoD-Loc mainly relies on high-LoD models, but the majority of available models and those many countries plan to construct nationwide are low-LoD (LoD1)<n>We introduce LoD-Loc v2, which employs a coarse-to-fine strategy using explicit silhouette alignment to achieve accurate localization over low-LoD city models in the air.
  arXiv  Detail & Related papers  (2025-07-01T10:56:51Z)
• Intern-GS: Vision Model Guided Sparse-View 3D Gaussian Splatting [95.61137026932062]
  Intern-GS is a novel approach to enhance the process of sparse-view Gaussian splatting.<n>We show that Intern-GS achieves state-of-the-art rendering quality across diverse datasets.
  arXiv  Detail & Related papers  (2025-05-27T05:17:49Z)
• LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment [16.942854458136633]
  We propose a new method for visual localization in complex 3D representations. Unlike existing localization algorithms, we estimate the pose of an Unmanned Vehicle (UAV) using a LevelDetail (LoD) 3D map.
  arXiv  Detail & Related papers  (2024-10-16T06:09:27Z)
• MegaScenes: Scene-Level View Synthesis at Scale [69.21293001231993]
  Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. We create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. We analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency.
  arXiv  Detail & Related papers  (2024-06-17T17:55:55Z)
• Dynamic 3D Gaussian Fields for Urban Areas [60.64840836584623]
  We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas. We propose 4DGF, a neural scene representation that scales to large-scale dynamic urban areas.
  arXiv  Detail & Related papers  (2024-06-05T12:07:39Z)
• ViiNeuS: Volumetric Initialization for Implicit Neural Surface reconstruction of urban scenes with limited image overlap [4.216707699421813]
  ViiNeuS is a new hybrid implicit surface learning method that efficiently initializes the signed distance field.<n>We show that ViiNeuS can learn an accurate and detailed 3D surface representation of various urban scene while being two times faster to train.
  arXiv  Detail & Related papers  (2024-03-15T14:31:17Z)
• Denoising Diffusion via Image-Based Rendering [54.20828696348574]
  We introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images.
  arXiv  Detail & Related papers  (2024-02-05T19:00:45Z)

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.