# Real or Not Real, that is the Question

arXiv: https://arxiv.org/abs/2002.05512 · HTML: https://mlsanity.com/paper/2002.05512/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 13 of 13)

- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [A survey on GANs for computer vision: Recent research, analysis and taxonomy](https://mlsanity.com/paper/2203.11242/) (2022)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [Model-adapted Fourier sampling for generative compressed sensing](https://mlsanity.com/paper/2310.04984/) (2023)
- [MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains](https://mlsanity.com/paper/2104.13742/) (2021)
- [Combating Mode Collapse in GANs via Manifold Entropy Estimation](https://mlsanity.com/paper/2208.12055/) (2022)
- [Hierarchical and Progressive Image Matting](https://mlsanity.com/paper/2210.06906/) (2022)
- [Hierarchical Perception Adversarial Learning Framework for Compressed Sensing MRI](https://mlsanity.com/paper/2302.10309/) (2023)
- [Towards Privacy-preserving Explanations in Medical Image Analysis](https://mlsanity.com/paper/2107.09652/) (2021)
- [Manifold-preserved GANs](https://mlsanity.com/paper/2109.08955/) (2021)
- [Dynamically Masked Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2306.07716/) (2023)
- [Denoising guarantees for optimized sampling schemes in compressed sensing](https://mlsanity.com/paper/2504.01046/) (2025)
- [Improving GAN Training via Feature Space Shrinkage](https://mlsanity.com/paper/2303.01559/) (2023)

## Abstract (arXiv)

While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. Compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving improvements on both synthetic and real-world datasets. Moreover, it enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.