Title: Towards Universal Place Recognition

Abstract:
Place Recognition is essential for achieving robust robot localization. However, current state-of-art systems remain environment/domain-specific and fragile. By leveraging insights from vision foundation models, we present AnyLoc, a universal VPR solution that performs across diverse environments without retraining or fine-tuning, significantly outperforming supervised baselines. We further introduce MultiLoc, and enable zero-shot cross modal place recognition across lidar and thermal modalities by distilling features from vision foundation models. Our comprehensive evaluation across structured and unstructured datasets demonstrates the feasibility of building universal place recognition systems that can operate anytime, anywhere, anyview and across any sensor.