FaceVision-GAN: A 3D Model Face Reconstruction Method from a Single Image Using GANs

التفاصيل البيبلوغرافية
العنوان: FaceVision-GAN: A 3D Model Face Reconstruction Method from a Single Image Using GANs
المؤلفون: Avola D., Cinque L., Foresti G. L., Marini M. R.
المساهمون: Avola, D., Cinque, L., Foresti, G. L., Marini, M. R.
بيانات النشر: Science and Technology Publications, Lda
سنة النشر: 2024
المجموعة: Università degli Studi di Udine: CINECA IRIS
مصطلحات موضوعية: 2D to 3D Reconstruction, 3D Modelling from Single Image, Face Syntesi, GAN
الوصف: Generative algorithms have been very successful in recent years. This phenomenon derives from the strong computational power that even consumer computers can provide. Moreover, a huge amount of data is available today for feeding deep learning algorithms. In this context, human 3D face mesh reconstruction is becoming an important but challenging topic in computer vision and computer graphics. It could be exploited in different application areas, from security to avatarization. This paper provides a 3D face reconstruction pipeline based on Generative Adversarial Networks (GANs). It can generate high-quality depth and correspondence maps from 2D images, which are exploited for producing a 3D model of the subject’s face.
نوع الوثيقة: conference object
اللغة: English
Relation: ispartofbook:International Conference on Pattern Recognition Applications and Methods; 13th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2024; volume:1; firstpage:628; lastpage:632; numberofpages:5; https://hdl.handle.net/11390/1275525; info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85190698598
DOI: 10.5220/0012306200003654
الاتاحة: https://hdl.handle.net/11390/1275525
https://doi.org/10.5220/0012306200003654
رقم الانضمام: edsbas.3FD908E7
قاعدة البيانات: BASE
الوصف
DOI:10.5220/0012306200003654