Neural Implicit Morphing of Face Images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Schardong, Guilherme, Novello, Tiago, Paz, Hallison, Medvedev, Iurii, da Silva, Vinícius, Velho, Luiz, Gonçalves, Nuno
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913513229778944
author Schardong, Guilherme
Novello, Tiago
Paz, Hallison
Medvedev, Iurii
da Silva, Vinícius
Velho, Luiz
Gonçalves, Nuno
author_facet Schardong, Guilherme
Novello, Tiago
Paz, Hallison
Medvedev, Iurii
da Silva, Vinícius
Velho, Luiz
Gonçalves, Nuno
contents Face morphing is a problem in computer graphics with numerous artistic and forensic applications. It is challenging due to variations in pose, lighting, gender, and ethnicity. This task consists of a warping for feature alignment and a blending for a seamless transition between the warped images. We propose to leverage coord-based neural networks to represent such warpings and blendings of face images. During training, we exploit the smoothness and flexibility of such networks by combining energy functionals employed in classical approaches without discretizations. Additionally, our method is time-dependent, allowing a continuous warping/blending of the images. During morphing inference, we need both direct and inverse transformations of the time-dependent warping. The first (second) is responsible for warping the target (source) image into the source (target) image. Our neural warping stores those maps in a single network dismissing the need for inverting them. The results of our experiments indicate that our method is competitive with both classical and generative models under the lens of image quality and face-morphing detectors. Aesthetically, the resulting images present a seamless blending of diverse faces not yet usual in the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13888
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Neural Implicit Morphing of Face Images
Schardong, Guilherme
Novello, Tiago
Paz, Hallison
Medvedev, Iurii
da Silva, Vinícius
Velho, Luiz
Gonçalves, Nuno
Computer Vision and Pattern Recognition
Machine Learning
I.4.8; I.4.10
Face morphing is a problem in computer graphics with numerous artistic and forensic applications. It is challenging due to variations in pose, lighting, gender, and ethnicity. This task consists of a warping for feature alignment and a blending for a seamless transition between the warped images. We propose to leverage coord-based neural networks to represent such warpings and blendings of face images. During training, we exploit the smoothness and flexibility of such networks by combining energy functionals employed in classical approaches without discretizations. Additionally, our method is time-dependent, allowing a continuous warping/blending of the images. During morphing inference, we need both direct and inverse transformations of the time-dependent warping. The first (second) is responsible for warping the target (source) image into the source (target) image. Our neural warping stores those maps in a single network dismissing the need for inverting them. The results of our experiments indicate that our method is competitive with both classical and generative models under the lens of image quality and face-morphing detectors. Aesthetically, the resulting images present a seamless blending of diverse faces not yet usual in the literature.
title Neural Implicit Morphing of Face Images
topic Computer Vision and Pattern Recognition
Machine Learning
I.4.8; I.4.10
url https://arxiv.org/abs/2308.13888