Home
Voxblox++ is a framework for building instance-level semantic maps from the RGB-D stream of a localized depth camera. The built maps not only accurately describe the geometry of the reconstructed scene, but additionally contain information about the individual object instances observed in the scene. In particular, the proposed framework retrieves the dense shape and pose of recognized semantic objects, as well as of newly discovered, previously unobserved object-like instances.
Get started with Voxblox++ on Ubuntu at the following page: Installation on Ubuntu 16.04 or 18.04.
Get Voxblox++ running following the instructions at: Basic usage.
Find out more about the different topics published by the Voxblox++ node and the available service calls at: The Voxblox++ node.