# Quality Prediction on Deep Generative Images

arXiv: https://arxiv.org/abs/2004.08245 · HTML: https://mlsanity.com/paper/2004.08245/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Going the Extra Mile in Face Image Quality Assessment: A Novel Database and Model](https://mlsanity.com/paper/2207.04904/) (2022)
- [NTIRE 2024 Quality Assessment of AI-Generated Content Challenge](https://mlsanity.com/paper/2404.16687/) (2024)
- [An Overview on Generative AI at Scale with Edge-Cloud Computing](https://mlsanity.com/paper/2306.17170/) (2023)
- [Perceptual Quality Improvement in Videoconferencing using Keyframes-based GAN](https://mlsanity.com/paper/2311.04263/) (2023)
- [You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment](https://mlsanity.com/paper/2310.09560/) (2023)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)
- [Visual Verity in AI-Generated Imagery: Computational Metrics and Human-Centric Analysis](https://mlsanity.com/paper/2408.12762/) (2024)

## Abstract (arXiv)

In recent years, deep neural networks have been utilized in a wide variety of applications including image generation. In particular, generative adversarial networks (GANs) are able to produce highly realistic pictures as part of tasks such as image compression. As with standard compression, it is desirable to be able to automatically assess the perceptual quality of generative images to monitor and control the encode process. However, existing image quality algorithms are ineffective on GAN generated content, especially on textured regions and at high compressions. Here we propose a new naturalness-based image quality predictor for generative images. Our new GAN picture quality predictor is built using a multi-stage parallel boosting system based on structural similarity features and measurements of statistical similarity. To enable model development and testing, we also constructed a subjective GAN image quality database containing (distorted) GAN images and collected human opinions of them. Our experimental results indicate that our proposed GAN IQA model delivers superior quality predictions on the generative image datasets, as well as on traditional image quality datasets.