# Improving generative adversarial network inversion via fine-tuning GAN encoders

arXiv: https://arxiv.org/abs/2108.10201 · HTML: https://mlsanity.com/paper/2108.10201/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 23 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [Pivotal Tuning for Latent-based Editing of Real Images](https://mlsanity.com/paper/2106.05744/) (2021)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Inverting The Generator Of A Generative Adversarial Network](https://mlsanity.com/paper/1611.05644/) (2016)
- [E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion](https://mlsanity.com/paper/2104.07661/) (2021)

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

- [The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations](https://mlsanity.com/paper/2409.12952/) (2024)
- [Understanding Diffusion Models via Code Execution](https://mlsanity.com/paper/2512.07201/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GANs) can synthesize high-quality (HQ) images, and GAN inversion is a technique that discovers how to invert given images back to latent space. While existing methods perform on StyleGAN inversion, they have limited performance and are not generalized to different GANs. To address these issues, we proposed a self-supervised method to pre-train and fine-tune GAN encoders. First, we designed an adaptive block to fit different encoder architectures for inverting diverse GANs. Then we pre-train GAN encoders using synthesized images and emphasize local regions through cropping images. Finally, we fine-tune the pre-trained GAN encoder for inverting real images. Compared with state-of-the-art methods, our method achieved better results that reconstructed high-quality images on mainstream GANs. Our code and pre-trained models are available at: https://github.com/disanda/Deep-GAN-Encoders.