# Evolutionary latent space search for driving human portrait generation

arXiv: https://arxiv.org/abs/2204.11887 · HTML: https://mlsanity.com/paper/2204.11887/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 7 of 7)

- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [StyleGAN2 Distillation for Feed-forward Image Manipulation](https://mlsanity.com/paper/2003.03581/) (2020)
- [Latent Space Exploration Using Generative Kernel PCA](https://mlsanity.com/paper/2105.13949/) (2021)
- [Conditional Generative Adversarial Networks to Model Urban Outdoor Air Pollution](https://mlsanity.com/paper/2010.02244/) (2020)

## Built on by (most cited first, 2 of 2)

- [An evolutionary model of personality traits related to cooperative behavior using a large language model](https://mlsanity.com/paper/2310.05976/) (2023)
- [Evolutionary ecology of words](https://mlsanity.com/paper/2505.05863/) (2025)

## Abstract (arXiv)

This article presents an evolutionary approach for synthetic human portraits generation based on the latent space exploration of a generative adversarial network. The idea is to produce different human face images very similar to a given target portrait. The approach applies StyleGAN2 for portrait generation and FaceNet for face similarity evaluation. The evolutionary search is based on exploring the real-coded latent space of StyleGAN2. The main results over both synthetic and real images indicate that the proposed approach generates accurate and diverse solutions, which represent realistic human portraits. The proposed research can contribute to improving the security of face recognition systems.