Generative AI for 3D Model Creation

Thesis Proposal Details

Supervisor: Simone Milani

Co-supervisor: Chiara Schiavo; Leonardo Monchieri; Elena Camuffo

Co-supervisor Department/Company: Simone Milani

Creation Date: 15/07/2025 22:15

Description

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:

1. Generation of 3D models within Gaussian framework.
2. Completion of Gaussian Splatting reconstructed scenes with in case of occluded objects.

Thesis require a preliminary knowledge of Computer Vision and Python programming.

Dataset and methods

Dataset type: Already acquired data

Dataset description: Multiview pictures taken from a given scene

List of Methods: 3D Gaussian Splatting, Generative Adversarial Networks, Diffusion Models

Preparatory Courses

3D Vision and eXtended Reality

Tags
3D AI Gaussian Generative Reconstruction Splatting
Back to proposals list