CSCPR: Cross-Source-Context Indoor RGB-D Place Recognition

TL;DR

CSCPR is a novel RGB-D indoor place recognition algorithm that integrates global retrieval with reranking, utilizing context-of-clusters for improved feature matching across cross-source and cross-scale data, outperforming existing methods.

Contribution

The paper introduces CSCPR, a new end-to-end model for RGB-D place recognition that incorporates novel reranking modules and applies context-of-clusters to handle cross-source and cross-scale data.

Findings

CSCPR outperforms state-of-the-art models by over 29% in Recall@1 on ScanNet-PR.

Introduces two datasets, ScanNetIPR and ARKitIPR, for indoor RGB-D place recognition.

Demonstrates significant accuracy improvements on multiple datasets.

Abstract

We extend our previous work, PoCo, and present a new algorithm, Cross-Source-Context Place Recognition (CSCPR), for RGB-D indoor place recognition that integrates global retrieval and reranking into an end-to-end model and keeps the consistency of using Context-of-Clusters (CoCs) for feature processing. Unlike prior approaches that primarily focus on the RGB domain for place recognition reranking, CSCPR is designed to handle the RGB-D data. We apply the CoCs to handle cross-sourced and cross-scaled RGB-D point clouds and introduce two novel modules for reranking: the Self-Context Cluster (SCC) and the Cross Source Context Cluster (CSCC), which enhance feature representation and match query-database pairs based on local features, respectively. We also release two new datasets, ScanNetIPR and ARKitIPR. Our experiments demonstrate that CSCPR significantly outperforms state-of-the-art models on these datasets by at least 29.27% in Recall@1 on the ScanNet-PR dataset and 43.24% in the new datasets. Code and datasets will be released.