Awesome-SLAM

SLAM code, paper, project collections

ORB-SLAM2 related codes

Raúl Mur-Artal and Juan D. Tardós. ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras. IEEE Transactions on Robotics,2017

PAPER, CODE, 中文注释版

改进方法

ORBSLAM2_with_pointcloud_map

ORB-SLAM2_RGBD_DENSE_MAP,modified from Xiang Gao's "ORB_SLAM2_modified".It is added a dense loopclosing map model

ORB-YGZ-SLAM, average 3x speed up and keep almost same accuracy v.s. ORB-SLAM2, use direct tracking in SVO to accelerate the feature matching

YGZ-stereo-inertial SLAM, LK optical flow + sliding window bundle adjustment

VIORB, An implementation of Visual Inertial ORBSLAM based on ORB-SLAM2

Fisheye-ORB-SLAM, A real-time robust monocular visual SLAM system based on ORB-SLAM for fisheye cameras, without rectifying or cropping the input images

Save and load orb-slam2 maps

ORB_SLAM2 with map load/save function

Viewer for maps from ORB-SLAM2 Osmap

ORB_SLAM2_SSD_Semantic, 动态语义SLAM 目标检测+VSLAM+光流/多视角几何动态物体检测+octomap地图+目标数据库

Add line feature based ORB-SLAM2

RGBD-SLAM with Point and Line Features, developed based on ORB_SLAM2

Different platforms

Windows version ORBSLAM2,Easy built by visual studio

ORB-SLAM-Android, test on Sony Xperia Z

ORBSLAM2 on Mac OSX

ROS interface for ORBSLAM2

Line feature based SLAM

PL-SLAM

Stereo visual SLAM using both point and line segment features

2017,PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments

PAPER, CODE

2016 IROS, PL-SVO: Semi-direct monocular visual odometry by combining points and line segments.

PAPER

2016 ICRA, Robust stereo visual odometry through a probabilistic combination of points and line segments. In Robotics and Automation

PAPER

PL-VIO

Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features

CODE

Monocular ORB-SLAM with Line Features

CODE

ORB_Line_SLAM

Add line feature based ORB-SLAM2

CODE

RGBD-PL-SLAM

RGBD-SLAM with Point and Line Features, developed based on the famous ORB_SLAM2

CODE

Line feature based RGBD-SLAM v2

CODE

3D Line Semi-dense SLAM

ICPR 2018, Incremental 3D Line Segment Extraction for Surface Reconstruction from Semi-dense SLAM

PAPER, , CODE

3D Line-based Stereo SLAM

2015 IEEE Transactions on Robotics, Building a 3-D Line-Based Map Using Stereo SLAM

CODE, 论文解读

LIDAR SLAM

2019

hdl_graph_slam

3D LIDAR-based Graph SLAM, real-time 6DOF SLAM using a 3D LIDAR 2019, Advanced Robotic Systems, [A Portable 3D LIDAR-based System for Long-term and Wide-area People Behavior Measurement, Advanced Robotic Systems

PAPER

LIO-mapping

ICRA 2019,A Tightly Coupled 3D Lidar and Inertial Odometry and Mapping Approach

PAPER, CODE

SuMa++

IROS 2019, SuMa++: Efficient LiDAR-based Semantic SLAM

PAPER, CODE

A-LOAM

Advanced implementation of LOAM, uses Eigen and Ceres Solver to simplify code structure. This code is modified from LOAM and LOAM_NOTED

CODE

2018

LeGO-LOAM

IROS 2018, LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain

CODE, PAPER, Video demo, Gif demo

loam_velodyne

Laser Odometry and Mapping (Loam) is a realtime method for state estimation and mapping using a 3D lidar

CODE

lidar_slam_3d

a ROS package for real-time 3D slam. It is based on NDT registration algorithm. With loop detection and back-end optimization, a map with global consistency can be generated.

CODE

2016

Google Cartographer Real-time 2D and 3D SLAM across multiple platforms and sensor configurations.

Real-Time Loop Closure in 2D LIDAR SLAM, in Robotics and Automation (ICRA), 2016 IEEE International Conference on. IEEE, 2016

PAPER, CODE, PROJECT

2D LaserSLAM

W.Hess, D.Kohler, H.Rapp and D.Andor. Real-Time Loop Closure in 2D LIDAR SLAM. ICRA, 2016

CODE, VIDEO

2014

LOAM

Laser Odometry And Mapping (LOAM) SLAM ROS package for 3D Velodyne VLP-16 laser scanner

J. Zhang and S. Singh. LOAM: Lidar Odometry and Mapping in Real-time. Robotics: Science and Systems Conference (RSS). Berkeley, CA, July 2014

PAPER, VIDEO, CODE, 中文注释代码

LIDAR-CAMERA SLAM

LIMO

2018 IROS, LIMO: Lidar-Monocular Visual Odometry

PAPER, CODE

VIO

OpenVINS, Monolar + IMU

An open source platform for visual-inertial navigation research.

2019 IROS, OpenVINS: A Research Platform for Visual-Inertial Estimation

PAPER, CODE, PROJECT

OpenVSLAM: A Versatile Visual SLAM Framework

1. A monocular, stereo, and RGBD visual SLAM system
2. Created maps can be stored and loaded

PAPER, CODE, VIDEO DEMO

3D reconstruction

Fastfusion

2014 ICRA, Volumetric 3D Mapping in Real-Time on a CPU

PAPER, CODE, Python wrapper

Intrinsic3D

Obtain high-quality 3D reconstructions from low-cost RGB-D sensors (with poses). The algorithm recovers fine-scale geometric details and sharp surface textures by simultaneously optimizing for reconstructed geometry, surface albedos, camera poses and scene lighting.

2017 ICCV, High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting

PAPER, CODE

Open3D

Open3D: A Modern Library for 3D Data Processing, Support C++, Python

Tutorial:A complete pipeline to reconstruct a 3D scene from an RGBD sequence

CODE

DenseSurfelMapping

Given a sequence of depth images, intensity images, and camera poses, the proposed methods can fuse them into a globally consistent model using surfel representation. The fusion method supports both ORB-SLAM2 and VINS-Mono.

2019 ICRA, Real-time Scalable Dense Surfel Mapping

PAPER, CODE

RGB-D SLAM

Bundle Adjusted Direct RGB-D SLAM

CVPR 2019, "BAD SLAM: Bundle Adjusted Direct RGB-D SLAM".

PAPER, CODE

StaticFusion

Basis for ElasticFusion.

2018 ICRA, StaticFusion: Background Reconstruction for Dense RGB-D SLAM in Dynamic Environments

CODE

CAMERA-IMU-LIDAR CALIBRATION

The Kalibr visual-inertial calibration toolbox

CODE