Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention

• URL: http://arxiv.org/abs/2505.17911v1
• Date: Fri, 23 May 2025 13:55:56 GMT
• Title: Object-level Cross-view Geo-localization with Location Enhancement and Multi-Head Cross Attention
• Abstract summary: Cross-view geo-localization determines the location of a query image, captured by a drone or ground-based camera, by matching it to a geo-referenced satellite image.<n>We propose an Object-level Cross-view Geo-localization Network (OCGNet) to address these challenges.<n>OCGNet achieves state-of-the-art performance on a public dataset, CVOGL.
• Score: 17.777115738099916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-view geo-localization determines the location of a query image, captured by a drone or ground-based camera, by matching it to a geo-referenced satellite image. While traditional approaches focus on image-level localization, many applications, such as search-and-rescue, infrastructure inspection, and precision delivery, demand object-level accuracy. This enables users to prompt a specific object with a single click on a drone image to retrieve precise geo-tagged information of the object. However, variations in viewpoints, timing, and imaging conditions pose significant challenges, especially when identifying visually similar objects in extensive satellite imagery. To address these challenges, we propose an Object-level Cross-view Geo-localization Network (OCGNet). It integrates user-specified click locations using Gaussian Kernel Transfer (GKT) to preserve location information throughout the network. This cue is dually embedded into the feature encoder and feature matching blocks, ensuring robust object-specific localization. Additionally, OCGNet incorporates a Location Enhancement (LE) module and a Multi-Head Cross Attention (MHCA) module to adaptively emphasize object-specific features or expand focus to relevant contextual regions when necessary. OCGNet achieves state-of-the-art performance on a public dataset, CVOGL. It also demonstrates few-shot learning capabilities, effectively generalizing from limited examples, making it suitable for diverse applications (https://github.com/ZheyangH/OCGNet).

Related papers

• InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization [12.259964756337892]
  Cross-view geo-localization is fundamental for precise localization and navigation in GPS-denied environments.<n>We propose InfoGeo, an information-theoretic framework designed to enhance robustness and generalization.<n> InfoGeo reformulates the optimization as an information bottleneck process with two core objectives: (i) maximizing view-invariant information by aligning the object-centric structural relations across views, and (ii) minimizing view-specific noisy signals through cross-view knowledge constraints.
  arXiv  Detail & Related papers  (2026-05-08T01:28:49Z)
• MOGeo: Beyond One-to-One Cross-View Object Geo-localization [27.10845184742442]
  Cross-View Object Geo-Localization (CVOGL) aims to locate an object of interest in a query image within a corresponding satellite image.<n>To bridge the gap between the realistic setting and existing task, we propose a new task, called Cross-View Multi-Object Geo-Localization (CVMOGL)<n>We propose a novel cross-view multi-object geo-localization method, MOGeo, and benchmark it against existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-14T08:54:16Z)
• G2HFNet: GeoGran-Aware Hierarchical Feature Fusion Network for Salient Object Detection in Optical Remote Sensing Images [76.1829298714382]
  Existing methods typically extract multi-level features at a single scale using uniform attention mechanisms.<n>We propose a GeoGran-Aware grained Feature Fusion Network (G2HFNet) that fully exploits geometric and granular cues in optical remote sensing images.
  arXiv  Detail & Related papers  (2026-03-13T05:52:00Z)
• GeoBridge: A Semantic-Anchored Multi-View Foundation Model Bridging Images and Text for Geo-Localization [36.20562550716618]
  Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image.<n>Traditional satellite-centric paradigm limits robustness when high-resolution or up-to-date satellite imagery is unavailable.<n>We propose GeoBridge, a model that performs bidirectional matching across views and supports language-to-image retrieval.
  arXiv  Detail & Related papers  (2025-12-02T12:28:22Z)
• Seeing the Unseen: Mask-Driven Positional Encoding and Strip-Convolution Context Modeling for Cross-View Object Geo-Localization [8.559240391514063]
  Cross-view object geo-localization enables high-precision object localization through cross-view matching.<n>Existing methods rely on keypoint-based positional encoding, which captures only 2D coordinates while neglecting object shape information.<n>We propose a mask-based positional encoding scheme that leverages segmentation masks to capture both spatial coordinates and object silhouettes.<n>We present EDGeo, an end-to-end framework for robust cross-view object geo-localization.
  arXiv  Detail & Related papers  (2025-10-23T06:07:07Z)
• DescribeEarth: Describe Anything for Remote Sensing Images [56.04533626223295]
  We propose Geo-DLC, a novel task of object-level fine-grained image captioning for remote sensing.<n>To support this task, we construct DE-Dataset, a large-scale dataset with detailed descriptions of object attributes, relationships, and contexts.<n>We also present DescribeEarth, a Multi-modal Large Language Model architecture explicitly designed for Geo-DLC.
  arXiv  Detail & Related papers  (2025-09-30T01:53:34Z)
• Anchor-free Cross-view Object Geo-localization with Gaussian Position Encoding and Cross-view Association [3.5982006325887554]
  We propose an anchor-free formulation for cross-view object geo-localization, termed AFGeo.<n> AFGeo directly predicts the four directional offsets to the ground-truth box for each pixel localizing the object without any predefined anchors.<n>Our model is both lightweight and efficient, achieving state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2025-09-30T00:30:45Z)
• VAGeo: View-specific Attention for Cross-View Object Geo-Localization [19.4845592498138]
  Cross-view object geo-localization (CVOGL) aims to locate an object of interest in a captured ground- or drone-view image within the satellite image.<n>This paper proposes a novel View-specific Attention Geo-localization method (VAGeo) for accurate CVOGL.
  arXiv  Detail & Related papers  (2025-01-13T10:42:18Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• United Domain Cognition Network for Salient Object Detection in Optical Remote Sensing Images [21.76732661032257]
  We propose a novel United Domain Cognition Network (UDCNet) to jointly explore the global-local information in the frequency and spatial domains. Experimental results demonstrate the superiority of the proposed UDCNet over 24 state-of-the-art models.
  arXiv  Detail & Related papers  (2024-11-11T04:12:27Z)
• GOMAA-Geo: GOal Modality Agnostic Active Geo-localization [49.599465495973654]
  We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. GOMAA-Geo is a goal modality active geo-localization agent for zero-shot generalization between different goal modalities.
  arXiv  Detail & Related papers  (2024-06-04T02:59:36Z)
• Detect2Interact: Localizing Object Key Field in Visual Question Answering (VQA) with LLMs [5.891295920078768]
  We introduce an advanced approach for fine-grained object visual key field detection. First, we use the segment anything model (SAM) to generate detailed spatial maps of objects in images. Next, we use Vision Studio to extract semantic object descriptions. Third, we employ GPT-4's common sense knowledge, bridging the gap between an object's semantics and its spatial map.
  arXiv  Detail & Related papers  (2024-04-01T14:53:36Z)
• GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization [61.10806364001535]
  Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. Existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task. We propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations.
  arXiv  Detail & Related papers  (2023-09-27T20:54:56Z)
• DQnet: Cross-Model Detail Querying for Camouflaged Object Detection [54.82390534024954]
  A convolutional neural network (CNN) for camouflaged object detection tends to activate local discriminative regions while ignoring complete object extent. In this paper, we argue that partial activation is caused by the intrinsic characteristics of CNN. In order to obtain feature maps that could activate full object extent, a novel framework termed Cross-Model Detail Querying network (DQnet) is proposed.
  arXiv  Detail & Related papers  (2022-12-16T06:23:58Z)
• CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization [89.69214577915959]
  This paper tackles the problem of Cross-view Video-based camera localization. We propose estimating the query camera's relative displacement to a satellite image before similarity matching. Experiments have demonstrated the effectiveness of video-based localization over single image-based localization.
  arXiv  Detail & Related papers  (2022-08-07T07:35:17Z)
• Visual and Object Geo-localization: A Comprehensive Survey [11.120155713865918]
  Geo-localization refers to the process of determining where on earth some entity' is located. This paper provides a comprehensive survey of geo-localization involving images, which involves either determining from where an image has been captured (Image geo-localization) or geo-locating objects within an image (Object geo-localization) We will provide an in-depth study, including a summary of popular algorithms, a description of proposed datasets, and an analysis of performance results to illustrate the current state of each field.
  arXiv  Detail & Related papers  (2021-12-30T20:46:53Z)
• Location-Sensitive Visual Recognition with Cross-IOU Loss [177.86369890708457]
  This paper proposes a unified solution named location-sensitive network (LSNet) for object detection, instance segmentation, and pose estimation. Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object.
  arXiv  Detail & Related papers  (2021-04-11T02:17:14Z)

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.