# Fine-Grained Expression Manipulation via Structured Latent Space

arXiv: https://arxiv.org/abs/2004.09769 · HTML: https://mlsanity.com/paper/2004.09769/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

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

- [3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation](https://mlsanity.com/paper/2209.05434/) (2022)
- [A Review of Human Emotion Synthesis Based on Generative Technology](https://mlsanity.com/paper/2412.07116/) (2024)
- [Talking Head Generation Driven by Speech-Related Facial Action Units and Audio- Based on Multimodal Representation Fusion](https://mlsanity.com/paper/2204.12756/) (2022)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)

## Abstract (arXiv)

Fine-grained facial expression manipulation is a challenging problem, as fine-grained expression details are difficult to be captured. Most existing expression manipulation methods resort to discrete expression labels, which mainly edit global expressions and ignore the manipulation of fine details. To tackle this limitation, we propose an end-to-end expression-guided generative adversarial network (EGGAN), which utilizes structured latent codes and continuous expression labels as input to generate images with expected expressions. Specifically, we adopt an adversarial autoencoder to map a source image into a structured latent space. Then, given the source latent code and the target expression label, we employ a conditional GAN to generate a new image with the target expression. Moreover, we introduce a perceptual loss and a multi-scale structural similarity loss to preserve identity and global shape during generation. Extensive experiments show that our method can manipulate fine-grained expressions, and generate continuous intermediate expressions between source and target expressions.