InterDigital Inc (IDCC)

[Gamco]

Findings from InterDigital Inc. Yields New Findings on Telecommunications (Facetunegan: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks): Telecommunications
[ NewsRx.com/Telecommunications Weekly]
Released: Monday, February 13, 2023 12:00 AM2023 FEB 13 (NewsRx) -- By a News Reporter-Staff News Editor at Telecommunications Daily -- Current study results on Telecommunications have been published. According to news reporting from Paris, France, by NewsRx journalists, research stated, "In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing and encoding separately facial identity and facial expression. We propose a first adaptation of image-to-image translation networks, that have successfully been used in the 2D domain, to 3D face geometry."
Financial supporters for this research include French National Research Agency (ANR), European Commission.
The news correspondents obtained a quote from the research from InterDigital Inc., "Leveraging recently released large face scan databases (FaceScape and CoMA), a neural network has been trained to decouple factors of variations with a better knowledge of the face, enabling facial expressions transfer and neutralization of expressive faces. Specifically, we design an
adversarial architecture adapting the base architecture of FUNIT and using SpiralNet++ for our convolutional and sampling operations. Applied on these two datasets, FaceTuneGAN has a better identity decomposition and face neutralization than state-of-the-art techniques."
According to the news reporters, the research concluded: “It also outperforms classical deformation transfer approach by predicting blendshapes closer to ground-truth data and with less of undesired artifacts due to too different facial morphologies between source and target.(."
This research has been peer-reviewed.
For more information on this research see: Facetunegan: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks. Computers & Graphics, 2023;110:69-85. Computers & Graphics can be contacted at: Pergamon-elsevier Science Ltd, The Boulevard, Langford Lane, Kidlington, Oxford OX5 1GB, England. (Elsevier - www.elsevier.com; Computers & Graphics - http://www.journals.elsevier.com/computers-and-graphics/)
Our news journalists report that additional information may be obtained by contacting Quentin Avril, InterDigital Inc., Paris,
France. Additional authors for this research include Nicolas Olivier, Kelian Baert, Fabien Danieau and Franck Multon.