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

arXiv: https://arxiv.org/abs/2608.11263 · HTML: https://mlsanity.com/paper/2608.11263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition](https://mlsanity.com/paper/2402.19231/) (2024)
- [Global visual localization in LiDAR-maps through shared 2D-3D embedding space](https://mlsanity.com/paper/1910.04871/) (2019)
- [LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localization](https://mlsanity.com/paper/2312.16648/) (2023)
- [General Place Recognition Survey: Towards Real-World Autonomy](https://mlsanity.com/paper/2405.04812/) (2024)
- [(LC)2: LiDAR-Camera Loop Constraints For Cross-Modal Place Recognition](https://mlsanity.com/paper/2304.08660/) (2023)
- [I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections](https://mlsanity.com/paper/2303.01043/) (2023)
- [SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition](https://mlsanity.com/paper/2502.16601/) (2025)
- [Place recognition survey: An update on deep learning approaches](https://mlsanity.com/paper/2106.10458/) (2021)
- [UniLoc: Towards Universal Place Recognition Using Any Single Modality](https://mlsanity.com/paper/2412.12079/) (2024)
- [ImLPR: Image-based LiDAR Place Recognition using Vision Foundation Models](https://mlsanity.com/paper/2505.18364/) (2025)
- [OneShot Global Localization: Instant LiDAR-Visual Pose Estimation](https://mlsanity.com/paper/2003.13279/) (2020)
- [VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition](https://mlsanity.com/paper/2403.14594/) (2024)

## Abstract (arXiv)

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.