# Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions

arXiv: https://arxiv.org/abs/1807.06650 · HTML: https://mlsanity.com/paper/1807.06650/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2018.

## Built on by (most cited first, 11 of 11)

- [CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models](https://mlsanity.com/paper/2404.15677/) (2024)
- [Few-shot Image Generation with Mixup-based Distance Learning](https://mlsanity.com/paper/2111.11672/) (2021)
- [A survey on GANs for computer vision: Recent research, analysis and taxonomy](https://mlsanity.com/paper/2203.11242/) (2022)
- [Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization](https://mlsanity.com/paper/2112.03163/) (2021)
- [A3D: Does Diffusion Dream about 3D Alignment?](https://mlsanity.com/paper/2406.15020/) (2024)
- [Connect the Dots: In Situ 4D Seismic Monitoring of CO2 Storage with Spatio-temporal CNNs](https://mlsanity.com/paper/2105.11622/) (2021)
- [Overcoming challenges in leveraging GANs for few-shot data augmentation](https://mlsanity.com/paper/2203.16662/) (2022)
- [Deep denoising autoencoder-based non-invasive blood flow detection for arteriovenous fistula](https://mlsanity.com/paper/2306.06865/) (2023)
- [Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space](https://mlsanity.com/paper/2307.15461/) (2023)
- [From Points to Spheres: A Geometric Reinterpretation of Variational Autoencoders](https://mlsanity.com/paper/2507.17255/) (2025)
- [Image Tokenizers Should Be Trained Between Images](https://mlsanity.com/paper/2610.16759/) (2026)

## Abstract (arXiv)

We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By using an AE as both the generator and discriminator of a GAN, we pass a pixel-wise error function across the discriminator, yielding an AE which produces non-blurry samples that match both high- and low-level features of the original images. Interpolations between images in this space remain within the latent-space distribution of real images as trained by the discriminator, and therfore preserve realistic resemblances to the network inputs. Code available at https://github.com/timsainb/GAIA