LEPA: Learning Geometric Equivariance in Satellite Remote Sensing Data with a Predictive Architecture

• URL: http://arxiv.org/abs/2603.07246v1
• Date: Sat, 07 Mar 2026 14:56:15 GMT
• Title: LEPA: Learning Geometric Equivariance in Satellite Remote Sensing Data with a Predictive Architecture
• Abstract summary: 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.
• Score: 2.618539394367099
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Geospatial foundation models provide precomputed embeddings that serve as compact feature vectors for large-scale satellite remote sensing data. While these embeddings can reduce data-transfer bottlenecks and computational costs, Earth observation (EO) applications can still face geometric mismatches between user-defined areas of interest and the fixed precomputed embedding grid. Standard latent-space interpolation is unreliable in this setting because the embedding manifold is highly non-convex, yielding representations that do not correspond to realistic inputs. We verify this using Prithvi-EO-2.0 to understand the shortcomings of interpolation applied to patch embeddings. As a substitute, we propose a Learned Equivariance-Predicting Architecture (LEPA). Instead of averaging vectors, LEPA conditions a predictor on geometric augmentations to directly predict the transformed embedding. We evaluate LEPA on NASA/USGS Harmonized Landsat-Sentinel (HLS) imagery and ImageNet-1k. Experiments show that standard interpolation achieves a mean reciprocal rank (MRR) below 0.2, whereas LEPA increases MRR to over 0.8, enabling accurate geometric adjustment without re-encoding.

Related papers

• Explainable Geospatial AI for Satellite Ground Station Siting Using LiDAR-Derived Terrain Intelligence [0.0]
  Representative clutter height (RCH) is a key parameter in radio propagation and interference analysis.<n>We present an interpretable, globally deployable machine learning framework for predicting RCH from open geospatial data.
  arXiv  Detail & Related papers  (2026-06-19T19:08:52Z)
• GeoRoPE: Ground-Aware Rotary Adaptation for Remote Sensing Foundation Models [34.24842271651431]
  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.
  arXiv  Detail & Related papers  (2026-06-08T12:15:53Z)
• 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)
• Sat-JEPA-Diff: Bridging Self-Supervised Learning and Generative Diffusion for Remote Sensing [0.0]
  Sat-JEPA-Diff combines Self-Supervised Learning (SSL) with Hidden Diffusion Models (LDM)<n>An IJEPA module predicts stable semantic representations, which then route a frozen Stable Diffusion backbone via a lightweight cross-attention adapter.<n> Evaluated on a global Sentinel-2 dataset, Sat-JEPA-Diff excels at resolving sharp boundaries.
  arXiv  Detail & Related papers  (2026-03-14T13:30:49Z)
• Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA [50.494504099850325]
  We introduce the Geodesic Hypothesis, positing that token sequences trace geodesics on a smooth semantic manifold and are therefore locally linear.<n>We show this constraint improves signal-to-noise ratio, and preserves diversity by preventing collisions during trajectory.<n>We demonstrate that geometric priors can surpass brute-force scaling.
  arXiv  Detail & Related papers  (2026-02-26T04:45:07Z)
• Inferring Height from Earth Embeddings: First insights using Google AlphaEarth [0.0]
  This study investigates whether the geospatial and multimodal features encoded in textitEarth Embeddings can effectively guide deep learning (DL) regression models for regional surface height mapping.<n>We focused on AlphaEarth Embeddings at 10 m spatial resolution and evaluated their capability to support height inference using a high-quality Digital Surface Model (DSM) as reference.<n>Both architectures achieved strong training performance (both with $R2 = 0.97$), confirming that the embeddings encode informative and decodable height-related signals.
  arXiv  Detail & Related papers  (2026-02-19T10:52:50Z)
• RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark [61.987291551925516]
  We introduce the Unit Cycle Resolver, which incorporates a unit circle constraint loss to improve angle prediction accuracy.<n>Our approach can effectively improve the performance of existing state-of-the-art weakly supervised methods.<n>With the aid of UCR, we further annotate and introduce RSAR, the largest multi-class rotated SAR object detection dataset to date.
  arXiv  Detail & Related papers  (2025-01-08T11:41:47Z)
• GeOT: A spatially explicit framework for evaluating spatio-temporal predictions [2.2766940909460986]
  We put forward Optimal Transport (OT) as a spatial evaluation metric and loss function.<n>The proposed framework assesses the performance of prediction models by quantifying the transport costs associated with their prediction errors.<n> Experiments with bike sharing, charging station, and traffic datasets show that spatial costs are significantly reduced with only marginal changes to non-spatial error metrics.
  arXiv  Detail & Related papers  (2024-10-15T15:46:03Z)
• OPUS: Occupancy Prediction Using a Sparse Set [64.60854562502523]
  We present a framework to simultaneously predict occupied locations and classes using a set of learnable queries. OPUS incorporates a suite of non-trivial strategies to enhance model performance. Our lightest model achieves superior RayIoU on the Occ3D-nuScenes dataset at near 2x FPS, while our heaviest model surpasses previous best results by 6.1 RayIoU.
  arXiv  Detail & Related papers  (2024-09-14T07:44:22Z)
• Relation DETR: Exploring Explicit Position Relation Prior for Object Detection [26.03892270020559]
  We present a scheme for enhancing the convergence and performance of DETR (DEtection TRansformer) Our approach, termed Relation-DETR, introduces an encoder to construct position relation embeddings for progressive attention refinement. Experiments on both generic and task-specific datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-07-16T13:17:07Z)
• Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction [82.72686460985297]
  We tackle the problem of estimating a Manhattan frame. We derive two new 2-line solvers, one of which does not suffer from singularities affecting existing solvers. We also design a new non-minimal method, running on an arbitrary number of lines, to boost the performance in local optimization.
  arXiv  Detail & Related papers  (2023-08-21T13:03:25Z)
• DAC: Detector-Agnostic Spatial Covariances for Deep Local Features [11.494662473750505]
  Current deep visual local feature detectors do not model the spatial uncertainty of detected features. We propose two post-hoc covariance estimates that can be plugged into any pretrained deep feature detector.
  arXiv  Detail & Related papers  (2023-05-20T17:43:09Z)
• Learning Signed Hyper Surfaces for Oriented Point Cloud Normal Estimation [53.19926259132379]
  We propose a novel method called SHS-Net for oriented normal estimation of point clouds by learning signed hyper surfaces. The signed hyper surfaces are implicitly learned in a high-dimensional feature space where the local and global information is aggregated. An attention-weighted normal prediction module is proposed as a decoder, which takes the local and global latent codes as input to predict oriented normals.
  arXiv  Detail & Related papers  (2023-05-10T03:40:25Z)
• Enhanced Laser-Scan Matching with Online Error Estimation for Highway and Tunnel Driving [0.0]
  Lidar data can be used to generate point clouds for navigation of autonomous vehicles or mobile robotics platforms. We propose the Iterative Closest Ellipsoidal Transform (ICET), a scan matching algorithm which provides two novel improvements.
  arXiv  Detail & Related papers  (2022-07-29T13:42:32Z)

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.