ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-02032022-093836


Tipo di tesi
Tesi di laurea magistrale
Autore
VELTRONI, ELENA
URN
etd-02032022-093836
Titolo
Design and implementation of a deep learning based 3D face reconstruction from 2D images
Dipartimento
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
ARTIFICIAL INTELLIGENCE AND DATA ENGINEERING
Relatori
relatore Prof. Falchi, Fabrizio
relatore Prof. Gennaro, Claudio
relatore Dott. Randellini, Enrico
Parole chiave
  • 3D reconstruction
  • 3D face reconstruction
Data inizio appello
18/02/2022
Consultabilità
Non consultabile
Data di rilascio
18/02/2025
Riassunto
Nowadays, 3D reconstruction from images has played an important role in computer vision with many improvements in both quality and performance. One of its main uses is the generation of 3D models of objects that are difficult to model.
This work mainly focuses on creating 3D models of human heads from 2D images using neural representations. However, these techniques have a significant limitation as their effectiveness is strictly dependent on the availability of a large number (several tens) of input views of the scene, and involve computationally expensive operations.
In this work, the specific problem of full 3D head reconstruction is addressed by adapting coordinate-based representations with a probabilistic prior that allows for faster convergence and better generalization when using few input images. The reconstruction is done in 2 steps, first we learn a 3D model of the head shape from different point clouds using implicit representations. After that, the learned prior is used to initialize and constrain the geometry of the reconstruction.
By doing so, we obtain high-fidelity reconstructions of the head, including the hair and shoulders, and with a high level of detail that exceeds state-of-the-art methods.
File