GeoUniPR: A Geometry-Consistent Unified Framework for Cross-Modal Place Recognition

• URL: http://arxiv.org/abs/2608.11263v1
• Date: Mon, 10 Aug 2026 03:52:01 GMT
• Title: GeoUniPR: A Geometry-Consistent Unified Framework for Cross-Modal Place Recognition
• Abstract summary: Cross-modal place recognition (CMPR) aims to identify the same location across heterogeneous sensing modalities, such as vision and LiDAR.<n>Existing methods commonly bridge the modality gap using complex alignment modules, multi-stage training, or full fine-tuning of pretrained backbones.<n>In this work, we propose GeoUniPR, a unified and concise geometry-consistent framework.
• Score: 8.76030434763729
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cross-modal place recognition (CMPR) aims to identify the same location across heterogeneous sensing modalities, such as vision and LiDAR. Existing methods commonly bridge the modality gap using complex alignment modules, multi-stage training, or full fine-tuning of pretrained backbones. In this work, we revisit CMPR from the perspective of geometric consistency and propose GeoUniPR, a unified and concise geometry-consistent framework. GeoUniPR reduces cross-modal discrepancy at the representation level by projecting LiDAR point clouds into the camera perspective to construct Geometry-Consistent depth image views (DIV), which establish direct RGB-LiDAR correspondence. We further augment DIV with native LiDAR cues, including intensity and surface-normal information, yielding a multi-channel geometric representation that improves structural consistency. Based on this representation, GeoUniPR learns a unified embedding space using two modality-specific ViT-based encoders with identical architectures, trained through parameter-efficient adaptation without auxiliary alignment modules, multi-stage training, or full backbone fine-tuning. In addition, we introduce Spatially-Consistent InfoNCE (SC-InfoNCE), a CMPR-specific contrastive objective that suppresses distance-induced false negatives under spatial continuity. Extensive experiments on KITTI and KITTI-360 demonstrate that GeoUniPR achieves state-of-the-art (SOTA) performance in both same-modal and cross-modal place recognition, with strong cross-dataset generalization.

Related papers

• GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment [32.33973839948303]
  Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints.<n>Existing methods typically fall into two extremes: voxel-based fusion provides explicit geometric alignment but requires costly 3D construction and class-specific assumptions.<n>We propose GeoMAD, a unified multi-view, multi-class AD framework that addresses both geometric correspondence deficiency and distributional inconsistency.
  arXiv  Detail & Related papers  (2026-08-27T07:15:15Z)
• More Than Where You Are: Learning Semantics, Structure, and Geometry from Cross-View Localization [8.17466031886622]
  Cross-view understanding under extreme viewpoint changes is essential for spatial intelligence.<n>We argue that cross-view localization should not be viewed merely as 2D matching or pose estimation.<n>We propose CROSS, a unified cross-view localization framework built upon 3D-grounded alignment, structure-aware matching, and hypothesis ranking.
  arXiv  Detail & Related papers  (2026-07-14T07:00:34Z)
• OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping [69.48762031013514]
  We propose OmniView-Space, a framework designed to maintain spatial consistency through multimodal egocentric evidence.<n>Our approach consists of three core components: (1) Multi-Perspective Spatial Mapping (MPSM), which re-anchors reconstructed geometry into a query-aligned visual cognitive map and a textual spatial graph; (2) Tool-Guided Egocentric Reasoning, an interleaved policy trained to actively select the ego anchor required by the query and request the corresponding MPSM evidence; and (3) Cognitive-Map Distillation, which uses MPSM-generated trajectories and ego-frame rewards to train the model to reason with self-generated cognitive maps
  arXiv  Detail & Related papers  (2026-07-01T12:45:12Z)
• G2IA: Geometry-Guided Instance-Aware Retrieval and Refinement for Cross-Modal Place Recognition [24.541278686912616]
  Cross-modal place recognition (CMPR) enables camera-only robots to localize against pre-built LiDAR maps in autonomous navigation scenarios.<n>This image-to-point-cloud setting is challenged by two ambiguities coupled: the modality gap between perspective RGB appearance and sparse metric geometry.<n>We propose G2IA, a geometry-guided instance-aware framework for image-to-point-cloud place recognition.
  arXiv  Detail & Related papers  (2026-06-13T12:53:52Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval [54.741349848771144]
  GeoMamba is a geometry-driven framework for optical-SAR fine-grained retrieval.<n>GFI module enhances cross-modal feature interaction and incorporates structural priors.<n>GeoMamba outperforms existing methods, achieving 63.3% mAP and 77.0% Rank-1 accuracy in all-to-all retrieval setting.
  arXiv  Detail & Related papers  (2026-05-19T12:08:09Z)
• UNIGEOCLIP: Unified Geospatial Contrastive Learning [23.04186252685893]
  Co-located geospatial data spans aerial imagery, street-level views, elevation models, text, and geographic coordinates.<n>We introduce UNIGEOCLIP, a massively multimodal contrastive framework to jointly align five complementary geospatial modalities.<n>We also propose a scaled latitude-longitude encoder that improves spatial representation by capturing multi-scale geographic structure.
  arXiv  Detail & Related papers  (2026-04-13T16:14:49Z)
• CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval [54.15776146365823]
  Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text.<n>We propose CSMCIR, a unified representation framework that achieves efficient query-target alignment through three synergistic components.
  arXiv  Detail & Related papers  (2026-01-07T09:21:38Z)
• Semantic-Enhanced Cross-Modal Place Recognition for Robust Robot Localization [1.2031796234206136]
  We introduce a framework we call Semantic-Enhanced Cross-Modal Place Recognition (SCM-PR)<n>SCM-PR combines high-level semantics utilizing RGB images for robust localization in LiDAR maps.<n>Our experimental work on the KITTI and KITTI-360 datasets show that SCM-PR achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-09-16T19:17:54Z)
• Dynamic Contrastive Learning for Hierarchical Retrieval: A Case Study of Distance-Aware Cross-View Geo-Localization [20.868592923432843]
  Existing deep learning-based cross-view geo-localization methods primarily focus on improving the accuracy of cross-domain image matching.<n>We propose Dynamic Contrastive Learning (DyCL), a novel framework that progressively aligns feature representations according to hierarchical spatial margins.
  arXiv  Detail & Related papers  (2025-06-29T03:57:01Z)
• Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation [50.433911327489554]
  The goal of referring remote sensing image segmentation (RRSIS) is to generate a pixel-level mask of the target object identified by the referring expression.<n>To address the aforementioned challenges, a novel RRSIS framework is proposed, termed the cross-modal bidirectional interaction model (CroBIM)<n>To further forster the research of RRSIS, we also construct RISBench, a new large-scale benchmark dataset comprising 52,472 image-language-label triplets.
  arXiv  Detail & Related papers  (2024-10-11T08:28:04Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)

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.