XiaoJake's repositories
vimo
!!首个联合估计机器人运动和外力的VIMO:Visual-Inertial Model-based State and External Forces Estimator
StanfordQuadruped
CAD 文件:https https://a360.co/2TEh4gQ
LARVIO
A lightweight, accurate and robust monocular visual inertial odometry based on Multi-State Constraint Kalman Filter.
SC-LeGO-LOAM
LiDAR SLAM: Scan Context + LeGO-LOAM
LiDAR-Iris
!!!Iris: 比ScanContext更加精确高效的激光回环检测方法LiDAR Iris for Loop-Closure Detection(IROS 2020)
kitti-lego-loam
Easy description to run and evaluate Lego-LOAM with KITTI-data
multi-task-refinenet
!使用不对称的注释数据集,实时联合进行语义分割和深度估计,处理速度超快:Multi-Task (Joint Segmentation / Depth / Surface Normas) Real-Time Light-Weight RefineNet
uav_trajectory_optimizer
!基于多逼真度模型的未知环境下实时路径规划:Efficient C++ solver to generate trajectories for UAVs
LINS---LiDAR-inertial-SLAM
A Lidar-Inertial State Estimator for Robust and Efficient Navigation based on iterated error-state Kalman filter
livox_horizon_loam
!livox激光的loam算法:Livox horizon porting for loam
SE-Sync
全局最优解问题:An implementation of the SE-Sync algorithm for synchronization over the special Euclidean group.
snn_angular_velocity
Event-Based Angular Velocity Regression with Spiking Networks
pointnet2
!!提出了多层次特征提取结构,有效提取局部特征提取,和全局特征PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
multi_lidar_calibration
!!多激光雷达外参自动标定:Multi lidar calibration tool from autoware, using NDT algorithm, need a approximate initial transformation
2D-3D-pose-tracking
!基于已知的激光雷达地图,用单目作2d-3d线匹配实现地图重定位:Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences
GSLAM
!!!通用slam框架: A General Simultaneous Localization and Mapping Framework which supports feature based or direct method and different sensors including monocular camera, RGB-D sensors or any other input types can be handled.
CentripetalNet
西交&商汤-基于向心偏移的anchor-free目标检测网络centripetalnet:Source codes of "CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection"
CenterMask
!maYOLACT实时实例分割检测器:CenterMask : Real-Time Anchor-Free Instance Segmentation, in CVPR 2020
frustum-pointnets
!!!F-PointNet将PointNet的应用拓展到了3D目标检测上,在进行点云处理之前,先使用图像信息得到一些先验搜索范围,这样既能提高效率,又能增加准确率:Frustum PointNets for 3D Object Detection from RGB-D Data
maskfusion
!基于RGBD的多动态目标识别,语义分割,跟踪的VSLAM系统:MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
DynamicRouting
!图像分割-动态路径方法解决图像中物体尺寸不一的问题:Learning Dynamic Routing for Semantic Segmentation
pwc
有代码的论文 Papers with code. Sorted by stars. Updated weekly.
rpg_e2vid
Code for the paper "High Speed and High Dynamic Range Video with an Event Camera" (T-PAMI, 2019).
FS3R
3D点云配准问题:A Fast Symbolic 3D Registration Solution from HKUST RAM-LAB
LeGO-LOAM-BOR
LeGO-LOAM-BOR: optimized Lidar Odometry and Mapping
lidar_car_platfrom
!!硬件平台:一个多激光雷达同时定位建图以及外参自标定的分布式框架
robot_pose_ekf
robot_pose_ekf package for ROS Melodic and later
SlideWindowOptimizationBased2DSLAM
A Slide Window Optimization Based 2D SLAM referred to VINS-FUSION implementation.
loam_livox
!!基于Livox的高效回环检测激光SLAM:A robust LiDAR Odometry and Mapping (LOAM) package for Livox-LiDAR