# UniLGL

**Repository Path**: janetmayle/UniLGL

## Basic Information

- **Project Name**: UniLGL
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-03-04
- **Last Updated**: 2026-03-04

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# UniLGL: Learning Uniform Place Recognition for FOV-limited/Panoramic LiDAR Global Localization

<p align="center">
<a href="https://arxiv.org/abs/2507.12194"><img src="https://img.shields.io/badge/ArXiv-2507.12194-b31b1b.svg?style=flat-square" alt="Arxiv" /></a>
<a href="https://youtu.be/p8D-sxq8ygI"><img src="https://badges.aleen42.com/src/youtube.svg" alt="YouTube" /></a>
<a href="https://www.bilibili.com/video/BV1Yw81zCEUv/"><img src="https://img.shields.io/badge/哔哩哔哩-Bilibili-fb7299" alt="Bilibili" /></a>
</p>

<div align="center">
<a href="https://youtu.be/p8D-sxq8ygI" target="_blank"><img src="doc/SystemOverview.jpg" alt="video" width="100%" /></a>
</div>

<!-- *Remark:* This results is running with single Livox Mid-70. -->
## Applications
UniLGL has been deployed on diverse platforms, including full-size trucks and agile MAVs, to enable high-precision localization and mapping as well as multi-MAV collaborative exploration in port and forest environments, demonstrating the applicability of UniLGL in industrial and field scenarios.
<div align="center">
<img src="doc/PSA-BEV-GIF.gif"  width="49.5%" />
<img src="doc/Multi-MAV-GIF.gif"  width="49.5%" />
</div>

## Additional Information
The code will be released soon. In addition, we will open-source a complete LiDAR-only SLAM system by integrating UniLGL with [CTE-MLO](https://github.com/shenhm516/CTE-MLO), which will be merged into the CTE-MLO repository.