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

TL;DR

PRFusion and PRFusion++ are innovative multi-modal place recognition models that effectively fuse image and point cloud data, demonstrating superior accuracy and robustness in challenging environments and outperforming existing methods on large-scale benchmarks.

Contribution

The paper introduces two novel multi-modal place recognition models that utilize global and local fusion techniques, incorporating neural diffusion layers for robustness, without requiring extrinsic calibration in one model.

Findings

Outperform existing models by +3.0 AR@1 on Boreas dataset.

Effective multi-modal fusion improves place recognition accuracy.

Neural diffusion layers enhance robustness in challenging environments.

Abstract

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