Alert button
Picture for Hallison Paz

Hallison Paz

Alert button

Neural Implicit Morphing of Face Images

Aug 26, 2023
Guilherme Schardong, Tiago Novello, Daniel Perazzo, Hallison Paz, Iurii Medvedev, Luiz Velho, Nuno Gonçalves

Figure 1 for Neural Implicit Morphing of Face Images
Figure 2 for Neural Implicit Morphing of Face Images
Figure 3 for Neural Implicit Morphing of Face Images
Figure 4 for Neural Implicit Morphing of Face Images

Face morphing is one of the seminal problems in computer graphics, with numerous artistic and forensic applications. It is notoriously challenging due to pose, lighting, gender, and ethnicity variations. Generally, this task consists of a warping for feature alignment and a blending for a seamless transition between the warped images. We propose to leverage coordinate-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, and blending of the target images. During warping inference, we need both direct and inverse transformations of the time-dependent warping. The first is responsible for morphing the target image into the source image, while the inverse is used for morphing in the opposite direction. Our neural warping stores those maps in a single network due to its inversible property, dismissing the hard task of inverting them. The results of our experiments indicate that our method is competitive with both classical and data-based neural techniques under the lens of face-morphing detection approaches. Aesthetically, the resulting images present a seamless blending of diverse faces not yet usual in the literature.

* 17 pages, 11 figures 
Viaarxiv icon

Multiresolution Neural Networks for Imaging

Aug 27, 2022
Hallison Paz, Tiago Novello, Vinicius Silva, Luiz Schirmer, Guilherme Schardong, Fabio Chagas, Helio Lopes, Luiz Velho

Figure 1 for Multiresolution Neural Networks for Imaging
Figure 2 for Multiresolution Neural Networks for Imaging
Figure 3 for Multiresolution Neural Networks for Imaging
Figure 4 for Multiresolution Neural Networks for Imaging

We present MR-Net, a general architecture for multiresolution neural networks, and a framework for imaging applications based on this architecture. Our coordinate-based networks are continuous both in space and in scale as they are composed of multiple stages that progressively add finer details. Besides that, they are a compact and efficient representation. We show examples of multiresolution image representation and applications to texturemagnification, minification, and antialiasing. This document is the extended version of the paper [PNS+22]. It includes additional material that would not fit the page limitations of the conference track for publication.

Viaarxiv icon