GeoRoPE: Ground-Aware Rotary Adaptation for Remote Sensing Foundation Models

• URL: http://arxiv.org/abs/2606.14760v1
• Date: Mon, 08 Jun 2026 12:15:53 GMT
• Title: GeoRoPE: Ground-Aware Rotary Adaptation for Remote Sensing Foundation Models
• Abstract summary: Remote-sensing foundation models (RSFMs) benefit from pretraining on imagery from multiple sensors and ground sampling (GSDs)<n>A fixed token-grid offset can correspond to different ground distances across sensors, making grid-based positional priors physically inconsistent.<n>We propose GeoRoPE, a ground-aware, RoPE-compatible, and parameter-efficient spatial adaptation method for RSFM.
• Score: 34.24842271651431
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Remote-sensing foundation models (RSFMs) benefit from pretraining on imagery from multiple sensors and ground sampling distances (GSDs), but such exposure alone does not resolve scale mismatch during downstream adaptation. A fixed token-grid offset can correspond to different ground distances across sensors, making grid-based positional priors physically inconsistent. Meanwhile, heterogeneous spatial granularity means that compact urban regions and homogeneous landscapes may require different positional sensitivities even under the same GSD. Therefore, we propose {GeoRoPE}, a ground-aware, RoPE-compatible, and parameter-efficient spatial adaptation method for RSFMs. GeoRoPE recalibrates token-level positional interactions from two complementary aspects. First, \textit{Geo-Coordinate Calibration (GCC)} rescales raw token-grid offsets according to the ground distance represented by one token-grid step, producing geo-calibrated relative coordinates across GSDs. Second, \textit{Geo-Frequency Calibration (GFC)} adjusts the native RoPE frequency with a relation-specific factor, enabling position sensitive adaptation to scene-dependent spatial granularity. GeoRoPE is injected into pretrained RSFMs through a lightweight adapter, preserving the frozen spatial prior while adding geo-aware positional corrections. Experiments across multiple RSFMs, sensors, resolutions, and downstream tasks demonstrate that GeoRoPE improves cross-resolution robustness and scale-sensitive representation learning.

Related papers

• ToPos: Automated Optimal Positioning on Topographic Manifolds using Constrained Geodesic Voronoi Decomposition [3.180674374101366]
  Reliable autonomous mapping, environmental last-mile logistics, and infrastructure deployment depend on the optimal surface area-balanced distribution of Spatial Reference Sites (SRS)<n>This paper introduces ToPos, an automated framework for TOPPos-aware Optimal Sampling on topographic obstructions.<n>The framework is architected as a Geographic Information System (GIS)-service to bolster the mentioned applications.
  arXiv  Detail & Related papers  (2026-09-04T12:38:48Z)
• 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)
• CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation [14.612259909790454]
  Cross-view geo-localization estimates the geographic location of a ground image by matching it against an aerial image database.<n>Existing methods tackle this through either large-scale retrieval or precise pose estimation, but not both.<n>We propose CIPER (Cross-view Image-retrieval and Pose-estimation transformER), a single architecture that jointly performs both tasks.
  arXiv  Detail & Related papers  (2026-06-03T15:31:06Z)
• FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales [65.4821703903285]
  FLORO is a multimodal foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus.<n> FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data.<n>We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks.
  arXiv  Detail & Related papers  (2026-05-27T08:55:54Z)
• URoPE: Universal Relative Position Embedding across Geometric Spaces [55.651792747815854]
  URoPE is a universal extension of Rotary Position Embedding (RoPE) to cross-view or cross-dimensional geometric spaces.<n>For each key/value image patch, URoPE samples 3D points along the corresponding camera ray at predefined depth anchors.<n>Standard 2D RoPE can then be applied using the projected pixel coordinates.
  arXiv  Detail & Related papers  (2026-04-20T18:52:03Z)
• 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)
• LEPA: Learning Geometric Equivariance in Satellite Remote Sensing Data with a Predictive Architecture [2.618539394367099]
  We propose a new architecture for predicting embeddings for large-scale satellite remote sensing data.<n>Instead of averaging, LEPA conditions a latent on embeddings to directly predict on NASA/USGS Landsat-Sentinel (HLS) imagery and LNet Image 0.8k.
  arXiv  Detail & Related papers  (2026-03-07T14:56:15Z)
• SMGeo: Cross-View Object Geo-Localization with Grid-Level Mixture-of-Experts [4.521626189942935]
  Cross-view object Geo-localization aims to precisely pinpoint the same object across large-scale satellite imagery based on drone images.<n>We present SMGeo, a promptable end-to-end transformer-based model for object Geo-localization.
  arXiv  Detail & Related papers  (2025-11-18T03:21:20Z)
• Geo2Vec: Shape- and Distance-Aware Neural Representation of Geospatial Entities [13.206124101350847]
  We introduce Geo2Vec, a novel method inspired by signed distance fields (SDF) that operates directly in the original space.<n>A neural network trained to approximate the SDF produces compact, geometry-aware, and unified representations for all geo-entity types.<n> Empirical results show that Geo2Vec consistently outperforms existing methods in representing shape and location, capturing topological and distance relationships, and achieving greater efficiency in real-world GeoAI applications.
  arXiv  Detail & Related papers  (2025-08-26T07:12:28Z)
• Performance and Generalizability Impacts of Incorporating Location Encoders into Deep Learning for Dynamic PM2.5 Estimation [0.39762912548964846]
  We study the effect of geolocation into deep learning for a dynamic and spatially heterogeneous application.<n>We estimate daily surface-level PM2.5 across the contiguous United States using satellite and ground-based observations.<n>Results show that raw coordinates can improve performance within regions by supporting spatial generalization, but can reduce generalizability across regions.
  arXiv  Detail & Related papers  (2025-05-24T02:00:34Z)
• SegDesicNet: Lightweight Semantic Segmentation in Remote Sensing with Geo-Coordinate Embeddings for Domain Adaptation [0.5461938536945723]
  We propose a novel unsupervised domain adaptation technique for remote sensing semantic segmentation.<n>Our proposed SegDesicNet module regresses the GRID positional encoding of the geo coordinates projected over the unit sphere to obtain the domain loss.<n>Our algorithm seeks to reduce the modeling disparity between artificial neural networks and human comprehension of the physical world.
  arXiv  Detail & Related papers  (2025-03-11T11:01:18Z)
• Information Entropy Initialized Concrete Autoencoder for Optimal Sensor Placement and Reconstruction of Geophysical Fields [58.720142291102135]
  We propose a new approach to the optimal placement of sensors for reconstructing geophysical fields from sparse measurements. We demonstrate our method on the two examples: (a) temperature and (b) salinity fields around the Barents Sea and the Svalbard group of islands. We find out that the obtained optimal sensor locations have clear physical interpretation and correspond to the boundaries between sea currents.
  arXiv  Detail & Related papers  (2022-06-28T12:43:38Z)
• Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection [121.28769542994664]
  Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance. In this paper, we are the first to reveal that the region proposal network (RPN) and region proposal classifier(RPC) demonstrate significantly different transferability when facing large domain gap.
  arXiv  Detail & Related papers  (2020-09-17T07:39:52Z)

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.