BabyNet: reconstructing 3D faces of babies from uncalibrated photographs

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Morales, Araceli
  • dc.contributor.author Alomar Adrover, Antònia
  • dc.contributor.author Porras Pérez, Antonio Reyes
  • dc.contributor.author Linguraru, Marius George
  • dc.contributor.author Piella Fenoy, Gemma
  • dc.contributor.author Sukno, Federico Mateo
  • dc.date.accessioned 2023-07-10T06:54:49Z
  • dc.date.available 2023-07-10T06:54:49Z
  • dc.date.issued 2023
  • dc.description.abstract 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.
  • dc.description.sponsorship This work is partly supported by the Spanish Ministry of Science and Innovation under project grant PID2020-114083GB-I00 and the NIH Eunice Kennedy Shriver National Institute of Child Health & Human Development grant R42 HD08171203. G. Piella is supported by ICREA under the ICREA Academia programme.
  • dc.format.mimetype application/pdf
  • dc.identifier.citation Morales A, Alomar A, Porras AR, Linguraru MG, Piella G, Sukno FM. BabyNet: reconstructing 3D faces of babies from uncalibrated photographs. Pattern Recognit. 2023;139:109367. DOI: 10.1016/j.patcog.2023.109367
  • dc.identifier.doi http://dx.doi.org/10.1016/j.patcog.2023.109367
  • dc.identifier.issn 0031-3203
  • dc.identifier.uri http://hdl.handle.net/10230/57511
  • dc.language.iso eng
  • dc.publisher Elsevier
  • dc.relation.ispartof Pattern Recognition. 2023;139:109367.
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PID2020-114083GB-I00
  • dc.rights This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
  • dc.rights.accessRights info:eu-repo/semantics/openAccess
  • dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/4.0/
  • dc.subject.keyword 3D face reconstruction
  • dc.subject.keyword Graph neural network
  • dc.subject.keyword Baby model
  • dc.title BabyNet: reconstructing 3D faces of babies from uncalibrated photographs
  • dc.type info:eu-repo/semantics/article
  • dc.type.version info:eu-repo/semantics/publishedVersion