# GIQA: Generated Image Quality Assessment

arXiv: https://arxiv.org/abs/2003.08932 · HTML: https://mlsanity.com/paper/2003.08932/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 30 of 51)

- [Vector Quantized Diffusion Model for Text-to-Image Synthesis](https://mlsanity.com/paper/2111.14822/) (2021)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [InstructDiffusion: A Generalist Modeling Interface for Vision Tasks](https://mlsanity.com/paper/2309.03895/) (2023)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions](https://mlsanity.com/paper/2306.05178/) (2023)
- [Face Forensics in the Wild](https://mlsanity.com/paper/2103.16076/) (2021)
- [Texturify: Generating Textures on 3D Shape Surfaces](https://mlsanity.com/paper/2204.02411/) (2022)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Improved Vector Quantized Diffusion Models](https://mlsanity.com/paper/2205.16007/) (2022)
- [ControlCom: Controllable Image Composition using Diffusion Model](https://mlsanity.com/paper/2308.10040/) (2023)
- [Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment](https://mlsanity.com/paper/2108.07948/) (2021)
- [StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis](https://mlsanity.com/paper/2206.09479/) (2022)
- [High-Fidelity and Arbitrary Face Editing](https://mlsanity.com/paper/2103.15814/) (2021)
- [Detecting and Recovering Sequential DeepFake Manipulation](https://mlsanity.com/paper/2207.02204/) (2022)
- [Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets](https://mlsanity.com/paper/2305.15407/) (2023)
- [SyncTweedies: A General Generative Framework Based on Synchronized Diffusions](https://mlsanity.com/paper/2403.14370/) (2024)
- [As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors](https://mlsanity.com/paper/2311.16739/) (2023)
- [Generative Uncertainty in Diffusion Models](https://mlsanity.com/paper/2502.20946/) (2025)
- [NTIRE 2024 Quality Assessment of AI-Generated Content Challenge](https://mlsanity.com/paper/2404.16687/) (2024)
- [TGIF: Text-Guided Inpainting Forgery Dataset](https://mlsanity.com/paper/2407.11566/) (2024)
- [Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks](https://mlsanity.com/paper/2305.12863/) (2023)
- [A Survey on Quality Metrics for Text-to-Image Generation](https://mlsanity.com/paper/2403.11821/) (2024)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [Improving Synthetically Generated Image Detection in Cross-Concept Settings](https://mlsanity.com/paper/2304.12053/) (2023)
- [CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP](https://mlsanity.com/paper/2408.15098/) (2024)
- [Assessing a Single Image in Reference-Guided Image Synthesis](https://mlsanity.com/paper/2112.04163/) (2021)
- [An Overview on Generative AI at Scale with Edge-Cloud Computing](https://mlsanity.com/paper/2306.17170/) (2023)
- [Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas](https://mlsanity.com/paper/2408.15660/) (2024)
- [Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity](https://mlsanity.com/paper/2312.06158/) (2023)
- [StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces](https://mlsanity.com/paper/2501.15445/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative model, but none of them are designed for a single generated image. In this paper, we propose a new research topic, Generated Image Quality Assessment (GIQA), which quantitatively evaluates the quality of each generated image. We introduce three GIQA algorithms from two perspectives: learning-based and data-based. We evaluate a number of images generated by various recent GAN models on different datasets and demonstrate that they are consistent with human assessments. Furthermore, GIQA is available to many applications, like separately evaluating the realism and diversity of generative models, and enabling online hard negative mining (OHEM) in the training of GANs to improve the results.