# Precise Recovery of Latent Vectors from Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1702.04782 · HTML: https://mlsanity.com/paper/1702.04782/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2017.

## Built on by (most cited first, 1 of 1)

- [Descriminative-Generative Custom Tokens for Vision-Language Models](https://mlsanity.com/paper/2502.12095/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GANs) transform latent vectors into visually plausible images. It is generally thought that the original GAN formulation gives no out-of-the-box method to reverse the mapping, projecting images back into latent space. We introduce a simple, gradient-based technique called stochastic clipping. In experiments, for images generated by the GAN, we precisely recover their latent vector pre-images 100% of the time. Additional experiments demonstrate that this method is robust to noise. Finally, we show that even for unseen images, our method appears to recover unique encodings.