# Region Based Adversarial Synthesis of Facial Action Units

arXiv: https://arxiv.org/abs/1910.10323 · HTML: https://mlsanity.com/paper/1910.10323/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2019.

## Built on by (most cited first, 4 of 4)

- [Talking Head Generation with Audio and Speech Related Facial Action Units](https://mlsanity.com/paper/2110.09951/) (2021)
- [Talking Head Generation Driven by Speech-Related Facial Action Units and Audio- Based on Multimodal Representation Fusion](https://mlsanity.com/paper/2204.12756/) (2022)
- [Face Super-Resolution with Progressive Embedding of Multi-scale Face Priors](https://mlsanity.com/paper/2210.06002/) (2022)
- [NeRF-AD: Neural Radiance Field with Attention-based Disentanglement for Talking Face Synthesis](https://mlsanity.com/paper/2401.12568/) (2024)

## Abstract (arXiv)

Facial expression synthesis or editing has recently received increasing attention in the field of affective computing and facial expression modeling. However, most existing facial expression synthesis works are limited in paired training data, low resolution, identity information damaging, and so on. To address those limitations, this paper introduces a novel Action Unit (AU) level facial expression synthesis method called Local Attentive Conditional Generative Adversarial Network (LAC-GAN) based on face action units annotations. Given desired AU labels, LAC-GAN utilizes local AU regional rules to control the status of each AU and attentive mechanism to combine several of them into the whole photo-realistic facial expressions or arbitrary facial expressions. In addition, unpaired training data is utilized in our proposed method to train the manipulation module with the corresponding AU labels, which learns a mapping between a facial expression manifold. Extensive qualitative and quantitative evaluations are conducted on the commonly used BP4D dataset to verify the effectiveness of our proposed AU synthesis method.