Digitising works of art helps to preserve cultural heritage, make art collections accessible and reinvent museum experiences.
As part of the ‘Métavers du patrimoine’ investment plan, experts are using photogrammetry to create 3D representations of works of art.
This project, which is being carried out with and for museums, takes into account the needs of institutions and adapts to their business model.
3D digitised works of art are not enough to create a metaverse; the challenge now is above all to discover the right uses for them.
The success of virtual museums will depend in particular on the democratisation of technologies such as VR headsets and the adaptation of platforms to the specific needs of museum institutions.
Professor of Computer Science at École Polytechnique (IP Paris) and member of the Académie des Sciences
Key takeaways
Computer graphics can be used to represent animated virtual spaces in 3D.
Collaboration with other scientific disciplines makes it possible to test and refine hypotheses by creating animated visual representations.
The modelling methodology is divided into three stages: multi-layer models, expressive modelling and learning from examples.
Expressive modelling provides scientists from other disciplines with the means to create their own animated 3D environments in line with their visions.
In the future, this field could, for example, become a major tool for increasing public awareness and involvement in environmental issues.
Professor at Télécom Paris (IP Paris) and Scientific Co-director of the Hi! PARIS interdisciplinary center for artificial intelligence
Key takeaways
AI applied to sound makes it possible to analyse, transform and synthesise sound signals.
The applications are numerous, ranging from predictive maintenance to virtual reality enhancement and personal assistance.
AI algorithms applied to sound require specific methods due to the temporal and voluminous nature of sound data.
The challenges associated with sound AI include its ecological impact, copyright issues, ethical concerns, and the need for an appropriate legal framework.
The HI-Audio project combines machine learning and human knowledge to create AI models that are more interpretable and controllable.
Subscribe to our weekly newsletterSubscribe to our weekly newsletter
