G2IA: Geometry-Guided Instance-Aware Retrieval and Refinement for Cross-Modal Place Recognition
For autonomous robots needing to localize camera images against LiDAR maps, G2IA addresses the coupled ambiguities of modality gap and perceptual aliasing, outperforming prior methods.
G2IA improves cross-modal place recognition (image-to-point-cloud) by integrating geometry-aware representation alignment and fine-grained instance verification, achieving consistent gains across benchmarks and strong cross-dataset generalization.
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.