NocPlace: Nocturnal Visual Place Recognition via Generative and Inherited Knowledge Transfer
This addresses the cross-domain night-to-day VPR problem for computer vision applications, but it is incremental as it builds on existing methods with dataset and fine-tuning enhancements.
The paper tackled the problem of Visual Place Recognition (VPR) degrading at night due to scarce nighttime images and cross-domain night-to-day issues, resulting in NocPlace improving Eigenplaces by 7.6% on Tokyo 24/7 Night and 16.8% on SVOX Night without added real-time resources.
Visual Place Recognition (VPR) is crucial in computer vision, aiming to retrieve database images similar to a query image from an extensive collection of known images. However, like many vision tasks, VPR always degrades at night due to the scarcity of nighttime images. Moreover, VPR needs to address the cross-domain problem of night-to-day rather than just the issue of a single nighttime domain. In response to these issues, we present NocPlace, which leverages generative and inherited knowledge transfer to embed resilience against dazzling lights and extreme darkness in the global descriptor. First, we establish a day-night urban scene dataset called NightCities, capturing diverse lighting variations and dark scenarios across 60 cities globally. Then, an image generation network is trained on this dataset and processes a large-scale VPR dataset, obtaining its nighttime version. Finally, VPR models are fine-tuned using descriptors inherited from themselves and night-style images, which builds explicit cross-domain contrastive relationships. Comprehensive experiments on various datasets demonstrate our contributions and the superiority of NocPlace. Without adding any real-time computing resources, NocPlace improves the performance of Eigenplaces by 7.6% on Tokyo 24/7 Night and 16.8% on SVOX Night.