loop-closure 开源项目推荐（74 个）

luigifreda /pyslam

pySLAM是一个混合了Python和C++语言的视觉SLAM解决方案，适用于单目、立体以及RGB-D类型的摄像头。它提供了多种现代局部和全局特征提取方法、多种循环闭合策略、体积重建模块、集成式的深度预测模型，以及语义分割功能，从而帮助更好地理解场景结构。

rsasaki0109 /lidar_slam_ros2

用于点云地图制作、基准测试和 Autoware 兼容地图工作流的 ROS 2 LiDAR SLAM。

hku-mars /STD

A 3D point cloud descriptor for place recognition

yanliang-wang /FAST_LIO_LC

The tight integration of FAST-LIO with Radius-Search-based loop closure module.

uoip /stereo_ptam

Python对SLAM算法Stereo-PTAM的实现

luigifreda /slamplay

slamplay is a collection of powerful tools to start playing and experimenting with SLAM in C++

rsasaki0109 /li_slam_ros2

ROS 2 package of tightly-coupled lidar inertial ndt/gicp slam

TixiaoShan /imaging_lidar_place_recognition

ICRA 2021 - Robust Place Recognition using an Imaging Lidar

GradientSpaces /LoopSplat

[3DV 2025, Oral] LoopSplat: Loop Closure by Registering 3D Gaussian Splats

xuhao1 /VINS-Fisheye

Fisheye version of VINS-Fusion

engcang /FAST-LIO-SAM-QN

A SLAM implementation combining FAST-LIO2 with pose graph optimization and loop closing based on Quatro and Nano-GICP

engcang /FAST-LIO-Localization-QN

A Map-based localization implementation combining FAST-LIO2 as an odometry with Quatro + Nano-GICP as a map matching method

mit-acl /clipper

graph-theoretic framework for robust pairwise data association

KumarRobotics /SLIDE_SLAM

SlideSLAM: Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multi-Robot Navigation

lewisjiang /contour-context

[ICRA'23] Official code repo for "Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation"

rpng /calc

Convolutional Autoencoder for Loop Closure

engcang /FAST-LIO-SAM-SC-QN

A SLAM implementation combining FAST-LIO2 with pose graph optimization and loop closing based on ScanContext, Quatro, and Nano-GICP

kajo-kurisu /D_VINS

将superpoint、lightglue、MixVPR合并到VINS-FUSION中，用TensorRT实现环路闭合

jyakaranda /ndt_map

SLAM package using NDT registration library of Autoware with loop-closure detection (odometry based) referenced from lego_loam.

PRBonn /online_place_recognition

Graph-based image sequences matching for the visual place recognition in changing environments.