# FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis

arXiv: https://arxiv.org/abs/1812.01288 · HTML: https://mlsanity.com/paper/1812.01288/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2018.

## Built on by (most cited first, 14 of 14)

- [ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis](https://mlsanity.com/paper/2103.05630/) (2021)
- [DCFace: Synthetic Face Generation with Dual Condition Diffusion Model](https://mlsanity.com/paper/2304.07060/) (2023)
- [GAN-Control: Explicitly Controllable GANs](https://mlsanity.com/paper/2101.02477/) (2021)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [DeepBlur: A Simple and Effective Method for Natural Image Obfuscation](https://mlsanity.com/paper/2104.02655/) (2021)
- [Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion](https://mlsanity.com/paper/2504.00430/) (2025)
- [Unsupervised Disentanglement of Linear-Encoded Facial Semantics](https://mlsanity.com/paper/2103.16605/) (2021)
- [EyePreserve: Identity-Preserving Iris Synthesis](https://mlsanity.com/paper/2312.12028/) (2023)
- [Rayleigh EigenDirections (REDs): GAN latent space traversals for multidimensional features](https://mlsanity.com/paper/2201.10423/) (2022)
- [Subjective Face Transform using Human First Impressions](https://mlsanity.com/paper/2309.15381/) (2023)
- [Sampling Strategies for Mitigating Bias in Face Synthesis Methods](https://mlsanity.com/paper/2405.11320/) (2024)
- [DALI-PD: Diffusion-based Synthetic Layout Heatmap Generation for ML in Physical Design](https://mlsanity.com/paper/2507.10606/) (2025)
- [Designing and Generating Diverse, Equitable Face Image Datasets for Face Verification Tasks](https://mlsanity.com/paper/2511.17393/) (2025)

## Abstract (arXiv)

The advance of Generative Adversarial Networks (GANs) enables realistic face image synthesis. However, synthesizing face images that preserve facial identity as well as have high diversity within each identity remains challenging. To address this problem, we present FaceFeat-GAN, a novel generative model that improves both image quality and diversity by using two stages. Unlike existing single-stage models that map random noise to image directly, our two-stage synthesis includes the first stage of diverse feature generation and the second stage of feature-to-image rendering. The competitions between generators and discriminators are carefully designed in both stages with different objective functions. Specially, in the first stage, they compete in the feature domain to synthesize various facial features rather than images. In the second stage, they compete in the image domain to render photo-realistic images that contain high diversity but preserve identity. Extensive experiments show that FaceFeat-GAN generates images that not only retain identity information but also have high diversity and quality, significantly outperforming previous methods.