A cross-domain visual place recognition (VPR) task is proposed in this work,
i.e., matching images of the same architectures depicted in different domains.
VPR is commonly treated as an image retrieval task, where a query image from an
unknown location is matched with relevant instance
VPR is crucial in computer vision, and this paper proposes NocPlace, a system that addresses the cross-domain problem of night-to-day in visual place recognition by leveraging a large-scale nighttime dataset to embed resilience against dazzling lights and extreme darkness, resulting in improved performance compared to previous methods.