AnyLoc: Towards Universal Visual Place Recognition

Visual Place Recognition (VPR) is vital for robot localization. To date, the most performant VPR approaches areenvironment- and task-specific:while they exhibit strong performance in structured environments (predominantly urban driving), their performance degrades severely in unstructured environments, rendering most approaches brittle to robust real-world deployment. In this work, we develop auniversalsolution to VPR – a technique that works across a broad range of structured and unstructured environments (urban, outdoors, indoors, aerial, underwater, and subterranean environments) without any re-training or finetuning. We demonstrate that general-purpose feature representations derived from off-the-shelf self-supervised modelswith no VPR-specific trainingare the right substrate upon which to build such a universal VPR solution. Combining these derived features withunsupervised feature aggregationenables our suite of methods,AnyLoc, to achieve up to4×significantly higher performance than existing approaches. We further obtain a 6% improvement in performance by characterizing the semantic properties of these features, uncovering uniquedomainswhich encapsulate datasets from similar environments. Our detailed experiments and analysis lay a foundation for building VPR solutions that may be deployedanywhere,anytime, and acrossanyview.