back to list
Project: Deep learning based 3D facial reconstruction
Description
Current approaches for facial reconstruction involve parametric modeling, where mathematical optimization is used to fit 3D morphable models to scanned point clouds of the face. In some cases, depth maps are
computed and 3D morphable models are then fitted on top of this map using conventional optimization
methodologies. Recent advancements have incorporated neural networks to fine-tune the parameters of
these models, moving us closer to achieving true-to-life facial reconstructions.
The aim of the project is to explore deep-learning methods for facial reconstruction, with applications to beauty science, as required by Innofaith; see detailed description below.
Detailed description
View PDFDetails
- Supervisor
-
Andrei Jalba
- Secondary supervisor
-
RIRonnie Edavattathu -- InnoFaith
- External location
- Innofaith
- Interested?
- Get in contact