Generative artificial intelligence (AI) models continue to gain popularity and recognition the recent release of services such as Google’s Imagen Video,  DALL-E, MidJourney and Stable Diffusion. Such algorithms can be adapted to the compression and transmission of image/video/audio signals, as well as 3D models for immersive and interactive applications.

The thesis work is going to focus on the use of generative algorithms (GANs, diffusion models, Implicit Neural Representation, Neural Radiance Field) in the characterization and optimization of multimedia contents, ranging from standard RGB images to light field datasets and point clouds.

For more information,  please contact prof. Simone Milani at simone.milani@dei.unipd.it.