Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks

Thumbnail Image

Files

SA-00270-DernelakisA.pdf (3.47 MB)

Links to Files

https://aaai-2022.virtualchair.net/poster_sa270

Permanent Link

http://hdl.handle.net/11603/25053

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Student Collection

Author/Creator

Author/Creator ORCID

Date

2022

Type of Work

journal articles
preprints
Text

Department

Program

Citation of Original Publication

"Dernelakis, et al. Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks. 36th AAAI Conference on Artificial Intelligence February 22 – March 1, 2022. https://aaai-2022.virtualchair.net/poster_sa270"

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Abstract

We propose a novel method for transforming the emotional content in an image to a specified target emotion. Existing techniques such as a single generative adversarial network (GAN) struggle to perform well on unconstrained images, especially when data is limited. Our method addresses this limitation by blending the outputs from two networks to better transform fine details (e.g., faces) while still operating on the broader styles of the full image. We demonstrate our method's potential through a proof-of-concept implementation.