TixiaoShan/LVI-SAM

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1875 stars · 512 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LVI-SAM is a tightly-coupled Lidar-Visual-Inertial Odometry and mapping system implemented in C++ on ROS, combining LIO-SAM and VINS-Mono at the system level. It fuses lidar, camera, and IMU data via factor-graph smoothing and mapping (GTSAM and Ceres) for real-time state estimation.

Use cases

• estimate robot trajectory from lidar, camera, and IMU data
• build 3D maps while localizing a mobile robot or handheld sensor rig
• run odometry on rosbag datasets from a Velodyne VLP-16 and camera/IMU suite
• fuse visual-inertial and lidar-inertial odometry for robust SLAM
• benchmark SLAM algorithms on public handheld and ground-robot datasets

When to choose

• you need robust odometry and mapping fusing lidar, camera, and IMU in a ROS pipeline
• your platform has all three sensor types and you want a proven, well-cited system
• you want a factor-graph SLAM baseline built on GTSAM and Ceres

When to avoid

• you only have a camera and IMU without lidar (use VINS-Mono instead)
• you need a maintained project with recent updates and support for newer ROS versions
• you need a pure lidar-inertial solution (use LIO-SAM instead)

Facets

application · maturity maintenance

simulation computer-vision graphics robotics autonomous-vehicles computer-vision cpp slam lidar-odometry visual-odometry sensor-fusion ros gtsam ceres-solver state-estimation linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="TixiaoShan/LVI-SAM")