CGiS-Net: Aggregating Colour, Geometry and Implicit Semantic Features for Indoor Place Recognition

TL;DR

This paper introduces CGiS-Net, a deep learning framework that combines colour, geometry, and semantic features from RGB point clouds to improve indoor place recognition accuracy significantly.

Contribution

It proposes a novel two-stage deep learning approach that leverages semantic segmentation to enhance feature discrimination for indoor place recognition.

Findings

Achieves a top-3 recall rate of 75%, outperforming previous methods.

Demonstrates the effectiveness of combining semantic features with geometry and colour.

Outperforms four state-of-the-art methods on the ScanNet-derived dataset.

Abstract

We describe a novel approach to indoor place recognition from RGB point clouds based on aggregating low-level colour and geometry features with high-level implicit semantic features. It uses a 2-stage deep learning framework, in which the first stage is trained for the auxiliary task of semantic segmentation and the second stage uses features from layers in the first stage to generate discriminate descriptors for place recognition. The auxiliary task encourages the features to be semantically meaningful, hence aggregating the geometry and colour in the RGB point cloud data with implicit semantic information. We use an indoor place recognition dataset derived from the ScanNet dataset for training and evaluation, with a test set comprising 3,608 point clouds generated from 100 different rooms. Comparison with a traditional feature-based method and four state-of-the-art deep learning methods demonstrate that our approach significantly outperforms all five methods, achieving, for example, a top-3 average recall rate of 75% compared with 41% for the closest rival method. Our code is available at: https://github.com/YuhangMing/Semantic-Indoor-Place-Recognition