We present a new algorithm, Cross-Source-Context Place Recognition (CSCPR), for RGB-D indoor place recognition that integrates global retrieval and reranking into a single end-to-end model. Unlike prior approaches that primarily focus on the RGB domain, CSCPR is designed to handle the RGB-D data. We extend the Context-of-Clusters (CoCs) for handling noisy colorized point clouds and introduce two novel modules for reranking: the Self-Context Cluster (SCC) and Cross Source Context Cluster (CSCC), which enhance feature representation and match query-database pairs based on local features, respectively. We also present two new datasets, ScanNetIPR and ARKitIPR. Our experiments demonstrate that CSCPR significantly outperforms state-of-the-art models on these datasets by at least 36.5% in Recall@1 at ScanNet-PR dataset and 44% in new datasets. Code and datasets will be released.

翻译：本文提出了一种用于RGB-D室内场景识别的新算法——跨源上下文场景识别（CSCPR），该算法将全局检索与重排序集成到一个端到端的统一模型中。与以往主要关注RGB领域的方法不同，CSCPR专为处理RGB-D数据而设计。我们扩展了上下文聚类（CoCs）方法以处理带噪声的彩色点云，并引入了两个新颖的重排序模块：自上下文聚类（SCC）和跨源上下文聚类（CSCC），分别用于增强特征表示和基于局部特征匹配查询-数据库对。我们还提出了两个新数据集：ScanNetIPR和ARKitIPR。实验结果表明，CSCPR在这些数据集上显著优于现有最先进模型，在ScanNet-PR数据集上的Recall@1指标至少提升36.5%，在新数据集上提升44%。代码与数据集将公开发布。