# One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN

arXiv: https://arxiv.org/abs/2010.11113 · HTML: https://mlsanity.com/paper/2010.11113/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion](https://mlsanity.com/paper/2104.07661/) (2021)
- [Intra-Source Style Augmentation for Improved Domain Generalization](https://mlsanity.com/paper/2210.10175/) (2022)
- [UnGANable: Defending Against GAN-based Face Manipulation](https://mlsanity.com/paper/2210.00957/) (2022)
- [Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization](https://mlsanity.com/paper/2307.00648/) (2023)
- [Generative Memory-Guided Semantic Reasoning Model for Image Inpainting](https://mlsanity.com/paper/2110.00261/) (2021)
- [In-Domain GAN Inversion for Faithful Reconstruction and Editability](https://mlsanity.com/paper/2309.13956/) (2023)
- [High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets](https://mlsanity.com/paper/2302.03406/) (2023)
- [Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data](https://mlsanity.com/paper/2107.06777/) (2021)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks. Different works have improved the limited understanding of the latent space of GANs by embedding images into specific GAN architectures to reconstruct the original images. We present a novel StyleGAN-based autoencoder architecture, which can reconstruct images with very high quality across several data domains. We demonstrate a previously unknown grade of generalizablility by training the encoder and decoder independently and on different datasets. Furthermore, we provide new insights about the significance and capabilities of noise inputs of the well-known StyleGAN architecture. Our proposed architecture can handle up to 40 images per second on a single GPU, which is approximately 28x faster than previous approaches. Finally, our model also shows promising results, when compared to the state-of-the-art on the image denoising task, although it was not explicitly designed for this task.