Can I read GSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving on EtoBox?

GSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving by Qi, Zhangshuo; Ma, Junyi; Xu, Jingyi; Zhou, Zijie; Cheng, Luqi; Xiong, Guangming is a scholarly article available to read on EtoBox.

What is GSPR: Multimodal Place Recognition Using 3D Gaussian Splatting for Autonomous Driving about?

Place recognition is a crucial component that enables autonomous vehicles to obtain localization results in GPS-denied environments. In recent years, multimodal place recognition methods have gained increasing attention. They overcome the weaknesses of unimodal sensor systems by leveraging complementary information from different modalities. However, most existing methods explore cross-modality correlations through feature-level or descriptor-level fusion, suffering from a lack of interpretability. Conversely, the recently proposed 3D Gaussian Splatting provides a new perspective on multimodal fusion by harmonizing different modalities into an explicit scene representation. In this paper, we propose a 3D Gaussian Splatting-based multimodal place recognition network dubbed GSPR. It explicitly combines multi-view RGB images and LiDAR point clouds into a spatio-temporally unified scene representation with the proposed Multimodal Gaussian Splatting. A network composed of 3D graph convolution and transformer is designed to extract spatio-temporal features and global descriptors from the Gaussian scenes for place recognition. Extensive evaluations on three datasets demonstrate that our m

Author

Qi, Zhangshuo; Ma, Junyi; Xu, Jingyi; Zhou, Zijie; Cheng, Luqi; Xiong, Guangming

Published

2024

Language

EN