# G2IA: Geometry-Guided Instance-Aware Retrieval and Refinement for Cross-Modal Place Recognition

arXiv: https://arxiv.org/abs/2606.15287 · HTML: https://mlsanity.com/paper/2606.15287/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 13 Jun 2026.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [MambaVision: A Hybrid Mamba-Transformer Vision Backbone](https://mlsanity.com/paper/2407.08083/) (2024)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [A Survey on Global LiDAR Localization: Challenges, Advances and Open Problems](https://mlsanity.com/paper/2302.07433/) (2023)
- [Text2Loc: 3D Point Cloud Localization from Natural Language](https://mlsanity.com/paper/2311.15977/) (2023)
- [LIP-Loc: LiDAR Image Pretraining for Cross-Modal Localization](https://mlsanity.com/paper/2312.16648/) (2023)
- [CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data](https://mlsanity.com/paper/2302.01665/) (2023)
- [(LC)2: LiDAR-Camera Loop Constraints For Cross-Modal Place Recognition](https://mlsanity.com/paper/2304.08660/) (2023)
- [LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition](https://mlsanity.com/paper/2311.03198/) (2023)
- [I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections](https://mlsanity.com/paper/2303.01043/) (2023)
- [General Place Recognition Survey: Towards the Real-world Autonomy Age](https://mlsanity.com/paper/2209.04497/) (2022)
- [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)
- [Tell Me Where You Are: Multimodal LLMs Meet Place Recognition](https://mlsanity.com/paper/2406.17520/) (2024)
- [ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognition](https://mlsanity.com/paper/2403.18762/) (2024)
- [OPAL: Visibility-aware LiDAR-to-OpenStreetMap Place Recognition via Adaptive Radial Fusion](https://mlsanity.com/paper/2504.19258/) (2025)
- [Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching](https://mlsanity.com/paper/2410.06285/) (2024)
- [VGGT-MPR: VGGT-Enhanced Multimodal Place Recognition in Autonomous Driving Environments](https://mlsanity.com/paper/2602.19735/) (2026)

## Abstract (arXiv)

Cross-modal place recognition (CMPR) enables camera-only robots to localize against pre-built LiDAR maps in autonomous navigation scenarios. This image-to-point-cloud setting is challenged by two coupled ambiguities: the modality gap between perspective RGB appearance and sparse metric geometry, and perceptual aliasing among urban places with similar roads, facades, intersections, and object arrangements. Instead of treating CMPR as a single global descriptor matching problem, we argue that reliable retrieval requires both geometry-aware representation alignment and fine-grained candidate verification. In this paper, we propose G2IA, a geometry-guided instance-aware framework for image-to-point-cloud place recognition. In the retrieval stage, visual geometry priors from VGGT and instance features are integrated to construct place descriptors that are more compatible with LiDAR-derived map representations. In the refinement stage, the retrieved candidates are re-ranked by explicitly verifying whether local instance shapes and their relative spatial layouts are consistent across modalities. Experiments on public benchmarks demonstrate that G2IA consistently improves image-to-point-cloud place recognition under different localization thresholds, and exhibits strong cross-dataset generalization.