Lidar SLAM
- Cartographer - Real-time SLAM in 2D and 3D across multiple platforms and sensor configurations [github cartographer]
- FAST-LIO - efficient and robust LiDAR-inertial odometry package [github FAST-LIO]
- LOL - Lidar-only Odometry and Localization in 3D point cloud maps [github lol]
- PyICP SLAM: Full-python LiDAR SLAM using ICP and Scan Context [github PyICP SLAM]
- LIO-SAM - Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping [github LIO-SAM]
- LeGO-LOAM - Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain [github LeGO-LOAM]
- hdl_graph_slam - 3D LIDAR-based Graph SLAM [github hdl_graph_slam]
- A-LOAM - Advanced implementation of LOAM [github A-LOAM]
- LIO-mapping - A Tightly Coupled 3D Lidar and Inertial Odometry and Mapping Approach [github LIO-mapping]
- SC-LeGO-LOAM - LiDAR SLAM: Scan Context + LeGO-LOAM [github SC-LeGO-LOAM]
- Fast LOAM: Fast and Optimized Lidar Odometry And Mapping for indoor/outdoor localization [github Fast LOAM]
- LINS: LiDAR-inertial-SLAM [github LINS]
VSLAM
- AprilSAM - Real-time smoothing and mapping [github xipengwang/AprilSAM]
- DSO - Novel direct and sparse formulation for Visual Odometry [github dso]
- ElasticFusion - Real-time dense visual SLAM system [github ElasticFusion]
- fiducials - Simultaneous localization and mapping using fiducial markers [github UbiquityRobotics/fiducials]
- GTSAM - Smoothing and mapping (SAM) in robotics and vision [github borglab/gtsam]
- Kintinuous - Real-time large scale dense visual SLAM system [github Kintinuous]
- LSD-SLAM - Real-time monocular SLAM [github lsdslam]
- ORB-SLAM2 - Real-time SLAM library for Monocular, Stereo and RGB-D cameras [github ORB_SLAM2]
- ORB-SLAM3 - Visual, Visual-Inertial and Multi-Map SLAM [github ORB_SLAM3]
- RTAP-Map - RGB-D Graph SLAM approach based on a global Bayesian loop closure detector [github introlab/rtabmap]
- SRBA - Solving SLAM/BA in relative coordinates with flexibility for different submapping strategies [github srba]
- DeepFactor - Real-Time Probabilistic Dense Monocular SLAM [github DeepFactor]
- ProSLAM - ProSLAM uses the lightning-fast, header-only HBST library for binary descriptor similarity search (loop closing) [github ProSlam]
- Vins-Mono - A Robust and Versatile Monocular Visual-Inertial State Estimator [github Vins-Mono]
- OpenVSLAM - A Versatile Visual SLAM Framework [github OpenVSLAM]
- Semantic SLAM - Semantic SLAM can generate a 3D voxel based semantic map using only a hand held RGB-D camera in real time [github Semantic Slam]
- ROVIO - Robust Visual Inertial Odometry [github ROVIO]
- LIFT-SLAM - a deep-learning feature-based monocular visual SLAM method [Paper LIFT-SLAM]
- SVO-SLAM - Fast Semi-Direct Monocular Visual Odometry [github SVO]
- MonoSLAM - real-time single camera SLAM [Paper MonoSLAM]
- CodeSLAM - Pytorch base SLAM [github CodeSLAM]
- Elbrus Stereo VSLAM - Elbrus is based on two core technologies: Visual Odometry (VO) and Simultaneous Localization and Mapping (SLAM). [nvidia link]
Object Detection
- Yolov4 - It is fast, easy to install, and supports CPU and GPU computation [github yolov4]
-DETR - End-to-End Object Detection with Transformers [github DETR] - Hydranets - The HydraNet is a neural network architecture that splits into multiple branches (or heads) close to the top of the network [github hydranets]
- CAM2BEV - A sim2real deep learning approach for the transformation of images from multiple vehicle-mounted camera to a semantically segmented image in bird's eye view [github cam2bev]
Depth estimation
- monodepth-1 - Unsupervised single image depth prediction [github monodepth1]
- monodepth-2 - self-supervised learning has emerged as a promising alternative for training models to perform monocular depth estimation. [github monodepth2]
- keras simple example [keras example]
Dataset
- SLAM datasets [Awesome-SLAM-datasets]
Awesome
3D Vision, VSLAM, Robotics, Deep_Learning