Live Collaborative Large-Scale Dense 3D Reconstruction Using Consumer-Grade Hardware

We present a real-time system for collaboratively reconstructing dense volumetric models of large 3D scenes (see Figure 1). Reconstructing such models is important for many tasks – e.g. content creation for films and games [10], augmented reality [19], cultural heritage preservation [21] and building information modelling [14] – but capturing large scenes can take significant time, and the risk of transient changes to the scene (e.g. people moving around) goes up as the capture time increases, corrupting the model and forcing the user to restart the capture. There are thus good reasons to want instead to split the capture into several shorter sequences, which can be captured either over multiple sessions or in parallel (by multiple users) and then joined to make the whole scene.