pith. sign in

arxiv: 1802.00390 · v1 · pith:NQ5JAR6Onew · submitted 2018-02-01 · 📡 eess.IV

Face Synthesis with Landmark Points from Generative Adversarial Networks and Inverse Latent Space Mapping

classification 📡 eess.IV
keywords facialfacelatentbeencorrespondinglandmarkspointsdataset
0
0 comments X
read the original abstract

Facial landmarks refer to the localization of fundamental facial points on face images. There have been a tremendous amount of attempts to detect these points from facial images however, there has never been an attempt to synthesize a random face and generate its corresponding facial landmarks. This paper presents a framework for augmenting a dataset in a latent Z-space and applied to the regression problem of generating a corresponding set of landmarks from a 2D facial dataset. The BEGAN framework has been used to train a face generator from CelebA database. The inverse of the generator is implemented using an Adam optimizer to generate the latent vector corresponding to each facial image, and a lightweight deep neural network is trained to map latent Z-space vectors to the landmark space. Initial results are promising and provide a generic methodology to augment annotated image datasets with additional intermediate samples.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.