PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Sijie, Kang, Qiyu, She, Rui, Zhao, Kai, Song, Yang, Tay, Wee Peng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913535548719104
author Wang, Sijie
Kang, Qiyu
She, Rui
Zhao, Kai
Song, Yang
Tay, Wee Peng
author_facet Wang, Sijie
Kang, Qiyu
She, Rui
Zhao, Kai
Song, Yang
Tay, Wee Peng
contents Place recognition plays a crucial role in the fields of robotics and computer vision, finding applications in areas such as autonomous driving, mapping, and localization. Place recognition identifies a place using query sensor data and a known database. One of the main challenges is to develop a model that can deliver accurate results while being robust to environmental variations. We propose two multi-modal place recognition models, namely PRFusion and PRFusion++. PRFusion utilizes global fusion with manifold metric attention, enabling effective interaction between features without requiring camera-LiDAR extrinsic calibrations. In contrast, PRFusion++ assumes the availability of extrinsic calibrations and leverages pixel-point correspondences to enhance feature learning on local windows. Additionally, both models incorporate neural diffusion layers, which enable reliable operation even in challenging environments. We verify the state-of-the-art performance of both models on three large-scale benchmarks. Notably, they outperform existing models by a substantial margin of +3.0 AR@1 on the demanding Boreas dataset. Furthermore, we conduct ablation studies to validate the effectiveness of our proposed methods. The codes are available at: https://github.com/sijieaaa/PRFusion
format Preprint
id arxiv_https___arxiv_org_abs_2410_04939
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusion
Wang, Sijie
Kang, Qiyu
She, Rui
Zhao, Kai
Song, Yang
Tay, Wee Peng
Computer Vision and Pattern Recognition
Place recognition plays a crucial role in the fields of robotics and computer vision, finding applications in areas such as autonomous driving, mapping, and localization. Place recognition identifies a place using query sensor data and a known database. One of the main challenges is to develop a model that can deliver accurate results while being robust to environmental variations. We propose two multi-modal place recognition models, namely PRFusion and PRFusion++. PRFusion utilizes global fusion with manifold metric attention, enabling effective interaction between features without requiring camera-LiDAR extrinsic calibrations. In contrast, PRFusion++ assumes the availability of extrinsic calibrations and leverages pixel-point correspondences to enhance feature learning on local windows. Additionally, both models incorporate neural diffusion layers, which enable reliable operation even in challenging environments. We verify the state-of-the-art performance of both models on three large-scale benchmarks. Notably, they outperform existing models by a substantial margin of +3.0 AR@1 on the demanding Boreas dataset. Furthermore, we conduct ablation studies to validate the effectiveness of our proposed methods. The codes are available at: https://github.com/sijieaaa/PRFusion
title PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.04939