# You Don't Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images

arXiv: https://arxiv.org/abs/2305.18337 · HTML: https://mlsanity.com/paper/2305.18337/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 9 of 9)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Are GANs Created Equal? A Large-Scale Study](https://mlsanity.com/paper/1711.10337/) (2017)
- [Synthetic Data -- Anonymisation Groundhog Day](https://mlsanity.com/paper/2011.07018/) (2020)

## Built on by (most cited first, 10 of 10)

- [Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models](https://mlsanity.com/paper/2403.13890/) (2024)
- [Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models](https://mlsanity.com/paper/2403.19508/) (2024)
- [Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2409.18872/) (2024)
- [Assessing the Efficacy of Invisible Watermarks in AI-Generated Medical Images](https://mlsanity.com/paper/2402.03473/) (2024)
- [PhytoSynth: Leveraging Multi-modal Generative Models for Crop Disease Data Generation with Novel Benchmarking and Prompt Engineering Approach](https://mlsanity.com/paper/2505.01823/) (2025)
- [Enhancing Super-Resolution Networks through Realistic Thick-Slice CT Simulation](https://mlsanity.com/paper/2307.10182/) (2023)
- [Efficiently Attacking Memorization Scores](https://mlsanity.com/paper/2509.20463/) (2025)
- [Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study](https://mlsanity.com/paper/2603.04340/) (2026)
- [Synthetic Cardiac MRI Image Generation using Deep Generative Models](https://mlsanity.com/paper/2603.24764/) (2026)
- [Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks](https://mlsanity.com/paper/2605.11898/) (2026)

## Abstract (arXiv)

Synthetic images generated from deep generative models have the potential to address data scarcity and data privacy issues. The selection of synthesis models is mostly based on image quality measurements, and most researchers favor synthetic images that produce realistic images, i.e., images with good fidelity scores, such as low Fr'echet Inception Distance (FID) and high Peak Signal-To-Noise Ratio (PSNR). However, the quality of synthetic images is not limited to fidelity, and a wide spectrum of metrics should be evaluated to comprehensively measure the quality of synthetic images. In addition, quality metrics are not truthful predictors of the utility of synthetic images, and the relations between these evaluation metrics are not yet clear. In this work, we have established a comprehensive set of evaluators for synthetic images, including fidelity, variety, privacy, and utility. By analyzing more than 100k chest X-ray images and their synthetic copies, we have demonstrated that there is an inevitable trade-off between synthetic image fidelity, variety, and privacy. In addition, we have empirically demonstrated that the utility score does not require images with both high fidelity and high variety. For intra- and cross-task data augmentation, mode-collapsed images and low-fidelity images can still demonstrate high utility. Finally, our experiments have also showed that it is possible to produce images with both high utility and privacy, which can provide a strong rationale for the use of deep generative models in privacy-preserving applications. Our study can shore up comprehensive guidance for the evaluation of synthetic images and elicit further developments for utility-aware deep generative models in medical image synthesis.