Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks (Student Abstract)

Aristidis Dernelakis, Jungin Kim, Kevin Velasquez, Lee Stearns

AAAI 2022 pp. 12933-12934

doi:10.1609/AAAI.V36I11.21603 /aaai/2022/dernelakis2022aaai-transformation/

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.

PDF AAAI Semantic Scholar

Cite

Text

Dernelakis et al. "Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21603

Markdown

[Dernelakis et al. "Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks (Student Abstract)." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/dernelakis2022aaai-transformation/) doi:10.1609/AAAI.V36I11.21603

BibTeX

@inproceedings{dernelakis2022aaai-transformation,
  title     = {{Transformation of Emotions in Images Using Poisson Blended Generative Adversarial Networks (Student Abstract)}},
  author    = {Dernelakis, Aristidis and Kim, Jungin and Velasquez, Kevin and Stearns, Lee},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {12933-12934},
  doi       = {10.1609/AAAI.V36I11.21603},
  url       = {https://mlanthology.org/aaai/2022/dernelakis2022aaai-transformation/}
}