Towards Localized Fine-Grained Control for Facial Expression Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Varanka, Tuomas, Khor, Huai-Qian, Li, Yante, Wei, Mengting, Kung, Hanwei, Sebe, Nicu, Zhao, Guoying
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929440791986176
author Varanka, Tuomas
Khor, Huai-Qian
Li, Yante
Wei, Mengting
Kung, Hanwei
Sebe, Nicu
Zhao, Guoying
author_facet Varanka, Tuomas
Khor, Huai-Qian
Li, Yante
Wei, Mengting
Kung, Hanwei
Sebe, Nicu
Zhao, Guoying
contents Generative models have surged in popularity recently due to their ability to produce high-quality images and video. However, steering these models to produce images with specific attributes and precise control remains challenging. Humans, particularly their faces, are central to content generation due to their ability to convey rich expressions and intent. Current generative models mostly generate flat neutral expressions and characterless smiles without authenticity. Other basic expressions like anger are possible, but are limited to the stereotypical expression, while other unconventional facial expressions like doubtful are difficult to reliably generate. In this work, we propose the use of AUs (action units) for facial expression control in face generation. AUs describe individual facial muscle movements based on facial anatomy, allowing precise and localized control over the intensity of facial movements. By combining different action units, we unlock the ability to create unconventional facial expressions that go beyond typical emotional models, enabling nuanced and authentic reactions reflective of real-world expressions. The proposed method can be seamlessly integrated with both text and image prompts using adapters, offering precise and intuitive control of the generated results. Code and dataset are available in {https://github.com/tvaranka/fineface}.
format Preprint
id arxiv_https___arxiv_org_abs_2407_20175
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Localized Fine-Grained Control for Facial Expression Generation
Varanka, Tuomas
Khor, Huai-Qian
Li, Yante
Wei, Mengting
Kung, Hanwei
Sebe, Nicu
Zhao, Guoying
Computer Vision and Pattern Recognition
Generative models have surged in popularity recently due to their ability to produce high-quality images and video. However, steering these models to produce images with specific attributes and precise control remains challenging. Humans, particularly their faces, are central to content generation due to their ability to convey rich expressions and intent. Current generative models mostly generate flat neutral expressions and characterless smiles without authenticity. Other basic expressions like anger are possible, but are limited to the stereotypical expression, while other unconventional facial expressions like doubtful are difficult to reliably generate. In this work, we propose the use of AUs (action units) for facial expression control in face generation. AUs describe individual facial muscle movements based on facial anatomy, allowing precise and localized control over the intensity of facial movements. By combining different action units, we unlock the ability to create unconventional facial expressions that go beyond typical emotional models, enabling nuanced and authentic reactions reflective of real-world expressions. The proposed method can be seamlessly integrated with both text and image prompts using adapters, offering precise and intuitive control of the generated results. Code and dataset are available in {https://github.com/tvaranka/fineface}.
title Towards Localized Fine-Grained Control for Facial Expression Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.20175