Download PDFOpen PDF in browser

Face Depth Estimation and 3-D reconstruction

EasyChair Preprint no. 3211

6 pagesDate: April 20, 2020


In the world of fast growing technology people look for more realistic representation and hence 3D representation of 2D images acquire great importance. 3D models are used in various fields like face recognition and animation games. They are widely used in medical industry to create interac- tive representations of anatomy. However, constructing 3D models or reconstructing from 2D images have been a major challenge for the researchers. Many approaches have been proposed and developed for generating 3D representation. In this work, we developed a Generator Adversarial Net- work(GAN) based method for depth map estimation from any given single face image.Here we have used pix2pix which is a variant of the conditional GAN.It is capable of performing image-to-image translation using the unsuper- vised method of machine learning.We found that it is the most robust method.

Keyphrases: 3D reconstruction, deep learning, Face Depth Estimation, GAN

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Alba Terese Baby and Aleesha Andrews and Amal Joseph and Amal Dinesh and V. K. Anjusree},
  title = {Face Depth Estimation and 3-D reconstruction},
  howpublished = {EasyChair Preprint no. 3211},

  year = {EasyChair, 2020}}
Download PDFOpen PDF in browser