hku-mars/FAST-LIVO

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1631 stars · 267 forks observed · 2026-08-28

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

FAST-LIVO is a fast, tightly-coupled sparse-direct LiDAR-Inertial-Visual Odometry system combining a LIO subsystem that registers raw points to an incrementally-built point cloud map and a VIO subsystem that aligns images via direct photometric error minimization. It is a C++/ROS research codebase from HKU MARS, published at IROS 2022, with a successor FAST-LIVO2 available.

Use cases

• estimate robot trajectory from lidar, camera, and IMU data
• build 3D point cloud maps with color from camera images
• perform real-time odometry for UAV navigation
• fuse lidar and camera measurements in a tightly-coupled SLAM system
• run odometry in degenerate lidar or camera scenarios
• reconstruct colored 3D environments from sensor data

When to choose

• you need real-time LiDAR-inertial-visual odometry with direct (feature-less) methods
• you want colored point cloud mapping from lidar-camera fusion
• you are doing UAV state estimation or onboard navigation research
• you work with Livox lidars and ROS on Ubuntu

When to avoid

• you need a production-supported product rather than research code
• you do not use ROS or Linux
• you want the latest accuracy improvements, in which case FAST-LIVO2 is preferable
• you need a visual SLAM system without a lidar sensor

Facets

library · maturity stable

simulation computer-vision image-processing robotics autonomous-vehicles computer-vision cpp slam lidar odometry sensor-fusion point-cloud visual-inertial-odometry lidar-inertial-odometry state-estimation uav algorithms linux ros

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hku-mars/FAST-LIVO")