A Quantitative comparison of methods for 3D face reconstruction from 2D images

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Morales, Araceli
• dc.contributor.author Piella Fenoy, Gemma
• dc.contributor.author Martínez, Oriol
• dc.contributor.author Sukno, Federico Mateo
• dc.date.accessioned 2021-03-19T07:17:47Z
• dc.date.available 2021-03-19T07:17:47Z
• dc.date.issued 2018
• dc.description Comunicació presentada a: 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) celebrat del 15 al 19 de maig a Xi'an, Xina.
• dc.description.abstract In the past years, many studies have highlighted the relation between deviations from normal facial morphology (dysmorphology) and some genetic and mental disorders. Recent advances in methods for reconstructing the 3D geometry of the face from 2D images opens new possibilities for dysmorphology research without the need for specialized 3D imaging equipment. However, it is unclear whether these methods could reconstruct the facial geometry with the required accuracy. In this paper we present a comparative study of some of the most relevant approaches for 3D face reconstruction from 2D images, including photometric-stereo, deep learning and 3D Morphable Model fitting. We address the comparison in qualitatively and quantitatively terms using a public database consisting of 2D images and 3D scans from 100 people. Interestingly, we find that some methods produce quite noisy reconstructions that do not seem realistic, whereas others look more natural. However, the latter do not seem to adequately capture the geometric variability that exists between different subjects and produce reconstructions that look always very similar across individuals, thus questioning their fidelity.en
• dc.description.sponsorship This work is partly supported by the Spanish Ministry of Economy and Competitiveness under project grant TIN2017-90124-P, the Ramon y Cajal programme, and the Maria de Maeztu Units of Excellence Programme (MDM2015-0502).
• dc.format.mimetype application/pdf
• dc.identifier.citation Morales A, Piella G, Martínez O, Sukno FM. A Quantitative comparison of methods for 3D face reconstruction from 2D images. In: 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018); 2018 May 15-19; Xi'an, China. Piscataway (NJ): IEEE; 2018. p. 731-8. DOI: 10.1109/FG.2018.00115
• dc.identifier.doi http://dx.doi.org/10.1109/FG.2018.00115
• dc.identifier.uri http://hdl.handle.net/10230/46852
• dc.language.iso eng
• dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
• dc.relation.ispartof 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018); 2018 May 15-19; Xi'an, China. Piscataway (NJ): IEEE; 2018. p. 731-8
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/TIN2017-90124-P
• dc.rights © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The final published article can be found at https://ieeexplore.ieee.org/document/8373908/.
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Three-dimensional displaysen
• dc.subject.keyword Faceen
• dc.subject.keyword Two dimensional displaysen
• dc.subject.keyword Image reconstructionen
• dc.subject.keyword Solid modelingen
• dc.subject.keyword Geometryen
• dc.subject.keyword Machine learningen
• dc.title A Quantitative comparison of methods for 3D face reconstruction from 2D imagesen
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion