Supervisor: Simone Milani
Co-supervisor: Chiara Schiavo; Leonardo Monchieri; Elena Camuffo
Co-supervisor Department/Company: Simone Milani
Creation Date: 15/07/2025 22:12
3D Gaussian splatting is a novel technique for real-time rendering of complex 3D scenes. It represents a scene as a collection of 3D Gaussian primitives, which are efficiently rendered to create high-quality, view-dependent images with impressive detail and speed.
The candidates that are interested on this thesis topics will focus on estimating the spatial occupancy of objects in a 3D
environment. Develop a simple shaped approximation
Thesis require a preliminary knowledge of Computer Vision and Python programming.
Dataset type: Already acquired data
Dataset description: multiview dataset of pictures acquired on a given scene
List of Methods: 3D Gaussian Splatting, segmentation
3D Vision & eXtended Reality