3D Reconstruction

Goal: starting with a few photographs of objects in everyday use, to create an algorithmic structure based on the Freudian model of the mind capable of interactively reconstructing the object in 3D in order to place it in augmented reality contexts
Use case

Computer vision and semantics for 3D object reconstruction (Freu3D)

Implemented algorithms

Recognition and positioning

Proprietary algorithm for recognising the object in the image and its positioning

Semantic

Proprietary algorithm for generating semantic attributes to be associated with the object identified in the image

3D Object Association

Proprietary algorithm for associating the object identified in the photograph with a corresponding 3D object through the use of semantic and positioning information

Data

Photographs of objects of daily use

  • Web interface for visualising the associations and reconstructions proposed by the algorithm
  • Web interface for exploring the generated 3D model and for acquiring individual navigation frames of the displayed model

Our Freu3d project is among the 18 projects selected in the European call for eXtended Reality technologies organised by XR4ALL, an initiative funded under the European Union’s Horizon 2020 research and innovation programme (Grant Agreement n. 825545).