BabyNet: reconstructing 3D faces of babies from uncalibrated photographs

We present a 3D face reconstruction system that aims at recovering the 3D facial geometry of babies from uncalibrated photographs, BabyNet. Since the 3D facial geometry of babies differs substantially from that of adults, baby-specific facial reconstruction systems are needed. BabyNet consists of tw...

Descripción completa

Detalles Bibliográficos
Autores: Morales, Araceli, Alomar Adrover, Antònia, Porras Pérez, Antonio Reyes, Linguraru, Marius George, Piella Fenoy, Gemma, Sukno, Federico Mateo
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2023
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/57511
Acceso en línea:http://hdl.handle.net/10230/57511
http://dx.doi.org/10.1016/j.patcog.2023.109367
Access Level:acceso abierto
Palabra clave:3D face reconstruction
Graph neural network
Baby model
Descripción
Sumario:We present a 3D face reconstruction system that aims at recovering the 3D facial geometry of babies from uncalibrated photographs, BabyNet. Since the 3D facial geometry of babies differs substantially from that of adults, baby-specific facial reconstruction systems are needed. BabyNet consists of two stages: 1) a 3D graph convolutional autoencoder learns a latent space of the baby 3D facial shape; and 2) a 2D encoder that maps photographs to the 3D latent space based on representative features extracted using transfer learning. In this way, using the pre-trained 3D decoder, we can recover a 3D face from 2D images. We evaluate BabyNet and show that 1) methods based on adult datasets cannot model the 3D facial geometry of babies, which proves the need for a baby-specific method, and 2) BabyNet outperforms classical model-fitting methods even when a baby-specific 3D morphable model, such as BabyFM, is used.