mlsanityData to 7 Oct 2026

Controlling Face's Frame generation in StyleGAN's latent space operations: Modifying faces to deceive our memory

arXiv 2407.00803 ↗First posted 30 Jun 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Innocence Project is a non-profitable organization that works in reducing wrongful convictions. In collaboration with Laboratorio de Sue~no y Memoria from Instituto Tecnol'ogico de Buenos Aires (ITBA), they are studying human memory in the context of face identification. They have a strong hypothesis stating that human memory heavily relies in face's frame to recognize faces. If this is proved, it could mean that face recognition in police lineups couldn't be trusted, as they may lead to wrongful convictions. This study uses experiments in order to try to prove this using faces with different properties, such as eyes size, but maintaining its frame as much as possible. In this project, we continue the work from a previous project that provided the basic tool to generate realistic faces using StyleGAN2. We take a deep dive into the internals of this tool to make full use of StyleGAN2 functionalities, while also adding more features, such as modifying certain of its attributes, including mouth-opening or eye-opening. As the usage of this tool heavily relies on maintaining the face-frame, we develop a way to identify the face-frame of each image and a function to compare it to the output of the neural network after applying some operations. We conclude that the face-frame is maintained when modifying eye-opening or mouth opening. When modifying vertical face orientation, gender, age and smile, have a considerable impact on its frame variation. And finally, the horizontal face orientation shows a major impact on the face-frame. This way, the Lab may apply some operations being confident that the face-frame won't significantly change, making them viable to be used to deceive subjects' memories.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 30 Jun 2024.

Builds on

18 of 36 references.

References · 18

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  11. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  12. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
6 more
  1. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  2. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  3. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  4. 2018Facial Landmark Detection: a Literature Surveycited by 63
  5. 2014On distinguishability criteria for estimating generative modelscited by 20
  6. 2022Face editing with GAN -- A Reviewcited by 1

Built on by

Not cited yet.