LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching

• URL: http://arxiv.org/abs/2608.04106v1
• Date: Tue, 04 Aug 2026 18:02:19 GMT
• Title: LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching
• Abstract summary: We present LoRetta, a foundation model coupling matchability-aware affine localization with guided dense registration.<n>We also introduce LEVIR-GM, a global-scale multi-temporal optical matching benchmark with dataset-native matchability labels.<n>On LEVIR-GM, LoRetta achieves an area under the curve (AUC) of 83.3%, outperforming the strongest baseline RoMa v2 by 1.6 points.
• Score: 39.25581475845445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dense image matching establishes pixel-wise correspondences and underpins broad applications in computer vision and photogrammetry. However, extending dense matching to global-scale remote sensing remains challenging because image pairs may differ in acquisition time, season, viewpoint, spatial resolution, and land-cover state. The resulting large geometric offsets, partial overlap, and intrinsically unmatchable regions make direct dense correspondence prediction unreliable and inefficient. We thus reformulate dense matching as localization-and-registration: first localizing the matchable overlap and affine geometry, then refining dense residuals within the aligned frame. Based on this formulation, we propose LoRetta, a foundation model coupling matchability-aware affine localization with guided dense registration. We also introduce LEVIR-GM, a global-scale multi-temporal optical matching benchmark with dataset-native matchability labels (103K aligned, 827K augmented pairs, six continents, five years, 0.5-1024 m resolution). We further establish a unified evaluation protocol for sparse, semi-dense, and dense matchers. On LEVIR-GM, LoRetta achieves an area under the curve (AUC) of 83.3%, outperforming the strongest baseline RoMa v2 by 1.6 points, with larger percentage of correct keypoints (PCK) gains of 6.5 and 8.2 points at 1 and 2 pixels, while reducing inference latency by 47.8%. Astronaut-to-satellite and unmanned aerial vehicle (UAV)-to-satellite geolocalization experiments further demonstrate its transferability as a reusable geometric aligner.

Related papers

• Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification [52.452902154360565]
  CARSANN is a geometry-driven framework that adapts the spatial support of each neighborhood according to local geometric complexity.<n>Experiments on more than 70 real-world OpenML datasets show that CARSANN consistently improves upon standard $k$-NN.
  arXiv  Detail & Related papers  (2026-08-27T19:19:07Z)
• RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs [8.321575653158094]
  Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention.<n>We address these shifts by sampling UAV-viewpoint reference views from Google 3D Tiles across locations, altitudes, and orientations.<n>A two-stage cross-domain fine-tuning recipe adapts SALAD using pose-near positives and geographically distant hard negatives, while local geometric consistency re-ranks the Top-K candidates.<n>We propose Retrieval-In-Matching (RIM), which freezes the adapted DINOv2-B retriever and distils a local-descriptor decoder that reuses its token field
  arXiv  Detail & Related papers  (2026-07-22T13:20:26Z)
• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• Globally Localizing Lunar Rover in Pixels via Graph Alignment [8.734737017643416]
  Cross-view localization provides a drift-free global solution by matching rover-view and satellite-view imagery.<n>We propose Warped Alignment of Reprojected Graphs (WARG), a framework that leverages unified graph learning and reprojected graph matching for robust cross-view alignment.
  arXiv  Detail & Related papers  (2026-06-09T09:04:54Z)
• Slum Detection and Density Mapping with AlphaEarth Foundations: A Representation Learning Evaluation Across 12 Global Cities [9.982796078979648]
  Pixel-level slum mapping has long been constrained by limited cross-city generalisation.<n>AlphaEarth Foundations offers a new analysis-ready basis for lightweight slum monitoring.<n>We evaluate AEF on slum classification and sub-pixel density estimation across 12 cities and 69 city-year pairs.
  arXiv  Detail & Related papers  (2026-05-11T05:54:15Z)
• Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception [51.687842983240564]
  Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) remains challenging due to the severe geometric discrepancy between oblique UAV imagery and satellite maps.<n>We propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation.<n>Our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
  arXiv  Detail & Related papers  (2026-04-02T08:08:41Z)
• iMatcher: Improve matching in point cloud registration via local-to-global geometric consistency learning [2.3985192761907643]
  iMatcher is a framework for feature matching in point cloud registration.<n>It uses both local and global consistency to predict a point-wise matching probability.<n>It achieves state-of-the-art inlier ratios, scoring 95% - 97% on KITTI, 94% - 97% on KITTI-360, and up to 81.1% on 3DMatch.
  arXiv  Detail & Related papers  (2025-09-10T20:25:57Z)
• SGAD: Semantic and Geometric-aware Descriptor for Local Feature Matching [16.683203139962153]
  We introduce the Semantic and Geometric-aware Descriptor Network (SGAD), which fundamentally rethinks area-based matching.<n>SGAD generates highly discriminative area descriptors that enable direct matching without complex graph optimization.<n>We further improve the performance of area matching through a novel supervision strategy that decomposes the area matching task into classification and ranking subtasks.
  arXiv  Detail & Related papers  (2025-08-04T10:46:53Z)
• AffineGlue: Joint Matching and Robust Estimation [74.04609046690913]
  We propose AffineGlue, a method for joint two-view feature matching and robust estimation. AffineGlue selects potential matches from one-to-many correspondences to estimate minimal models. Guided matching is then used to find matches consistent with the model, suffering less from the ambiguities of one-to-one matches.
  arXiv  Detail & Related papers  (2023-07-28T08:05:36Z)
• Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image [91.29546868637911]
  This paper addresses the problem of vehicle-mounted camera localization by matching a ground-level image with an overhead-view satellite map. The key idea is to formulate the task as pose estimation and solve it by neural-net based optimization. Experiments on standard autonomous vehicle localization datasets have confirmed the superiority of the proposed method.
  arXiv  Detail & Related papers  (2022-04-10T19:16:58Z)

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.