VGGT-SLAM测试

Code accompanying the paper entitled LEVIO: Lightweight Embedded Visual Inertial Odometry for Resource-Constrained Devices

ZED2 or D455 + livox_lidar for semantic mapping

LOAM and Mask R-CNN Semantic Mapping: semantic labelling for lidar point cloud with a color and a depth camera.

Cuda mesh utils.

!!! gs快速训练的slam [CVPR 2026] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

[2026 RA-L] LiDAR VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mapping

Support robosense LiDAR including M1, E1R, and Airy

A quadruped SLAM dataset covering diverse locomotion behaviors in complex environments

Open-source CUDA compiler targeting multiple GPU architectures. Compiles .cu to AMD and Tenstorrent GPU's

Make all Android phones capable of SLAM, point cloud scanning, and relocalization projects.

Real-time voxel mapping from Fast-LIO odometry using NVIDIA NVBlox on ROS 2. Converts LiDAR point clouds + Fast-LIO poses into TSDF/ESDF voxel maps for navigation and visualization.

[CVPR 2022] PointCLIP: Point Cloud Understanding by CLIP

Camera Drivers For NVIDIA Jetson Devices.

针对ros2的 rviz2、rqt web版本开源方案

针对ros2的 rviz2、rqt web版本开源方案

fast library for ANN search and KNN graph construction

kalibr标定工具的ros2 humble版本

A Resilient SLAM Framework

Adapter and benchmark hub for solid-state LiDAR across LIO/LVIO/SLAM, with robust handling for small-FoV short-range and degenerate scenarios.

Changhee Won, Jongbin Ryu and Jongwoo Lim "End-to-End Learning for Omnidirectional Stereo Matching with Uncertainty Prior", in TPAMI (ICCV 19)

[CVPR2021] Real-Time Sphere Sweeping Stereo from Multiview Fisheye Images

An unofficial PyTorch implementation of ICCV 2019 paper "OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching"