V4RL Code Releases
At V4RL we recularly release our datasets, code, and the setups that we use to encourage benchmarking. Here you can find all of our code releases, while this link details all our released datasets, and this link lists our setups.
COVINS: A Framework for Collaborative Visual-Inertial SLAM and Multi-Agent 3D Mapping
COVINS is an accurate, scalable, and versatile visual-inertial collaborative SLAM system, that enables a group of agents, equipped with visual and inertial sensing, to simultaneously co-localize and jointly map an environment. more
Event-based Feature Tracking
This code release contains the implementation multi-hypothesis ecent-based feature tracking. more
Multi-robot Coordination for Autonomous Navigation in Partially Unknown Environments
This multi-agent, centralized coordination framework performs state estimation, mapping nad path-planning for a small team of robots. Assuming that each robot is equipped with a monocular camera, an IMU, GPS and a depth sensor, this framework can co-localize the robots in a geo-referenced reference frame and create a joint globally consistent map of the environment by fusing the experiences of the individual agents. more
Aerial Single-view Depth Completion
In this work, we propose a powerful methodology for depth completion and uncertainty estimation approach that better handles the challenges of mapping from aerial vehicles, such as large viewpoint and depth variations, and limited computing resources. We publicly release our code, datasets and simulator to aid benchmarking. more
CCM-SLAM: Centralized Collaborative Monocular SLAM for Robotic Teams
This is a centralized collaborative SLAM framework for a team of robots, each equipped with monocular camera. These robots can employ CCM-SLAM to co-localize, while building a 3D map of their surroundings in real-time, in a collaborative fashion by sharing their experiences of the environment with each other. more
Visual-Inertial Relative Pose Estimation for Aerial Vehicles
Driven by the need for portable and low-cost solutions to relative pose estimation between Unmanned Aerial Vehicles (UAVs), in this codebase you can find a new framework to track a master UAV in real-time, carrying a known constellation of LED markers, from a slave UAV without any other pose estimation capability more...
Real-time Mesh-based Scene Estimation
Using a the feature-based map of a nominal keyframe-based SLAM system as an input, this software creates a very fast mesh-representation of the scene, while filtering out aparently erroneous mesh facades. This has been reported to run at 8ms per frame on a standard laptop (CPU only). This software is released under a GPLv3 (free for research purposes) more ...