# PanoDiff-SR: Synthesizing Dental Panoramic Radiographs using Diffusion and Super-resolution

arXiv: https://arxiv.org/abs/2507.09227 · HTML: https://mlsanity.com/paper/2507.09227/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 12 Jul 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Diffusion Probabilistic Models beat GANs on Medical Images](https://mlsanity.com/paper/2212.07501/) (2022)
- [Adversarial Examples that Fool both Computer Vision and Time-Limited Humans](https://mlsanity.com/paper/1802.08195/) (2018)
- [HAT: Hybrid Attention Transformer for Image Restoration](https://mlsanity.com/paper/2309.05239/) (2023)
- [DENTEX: Dental Enumeration and Tooth Pathosis Detection Benchmark for Panoramic X-ray](https://mlsanity.com/paper/2305.19112/) (2023)
- [Curved Diffusion: A Generative Model With Optical Geometry Control](https://mlsanity.com/paper/2311.17609/) (2023)
- [Osmosis: RGBD Diffusion Prior for Underwater Image Restoration](https://mlsanity.com/paper/2403.14837/) (2024)
- [TwinDiffusion: Enhancing Coherence and Efficiency in Panoramic Image Generation with Diffusion Models](https://mlsanity.com/paper/2404.19475/) (2024)
- [License Plate Images Generation with Diffusion Models](https://mlsanity.com/paper/2501.03374/) (2025)

## Built on by (most cited first, 2 of 2)

- [SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis](https://mlsanity.com/paper/2512.17585/) (2025)
- [Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation](https://mlsanity.com/paper/2605.04201/) (2026)

## Abstract (arXiv)

Interest in generating realistic synthetic medical images has grown in recent years. Such datasets can mitigate the scarcity of public data for artificial intelligence research and support education. Work on synthesizing dental panoramic radiographs (PRs) has so far relied almost exclusively on generative adversarial networks (GANs), and three limitations recur: the synthesized field of view is often restricted to a cropped dentoalveolar region rather than a complete PR; observer studies of GAN-generated PRs report that clinicians still identify synthetic images with accuracies of roughly 78-82%, implying persistent visible giveaways; and adversarial training remains sensitive to instability and mode collapse. Generating a full-size PR directly at diagnostic resolution with a diffusion model is an alternative, but sampling at that resolution is costly. We therefore present PanoDiff-SR, an end-to-end two-stage pipeline developed and evaluated specifically for panoramic radiography: a denoising diffusion implicit model (PanoDiff) generates a low-resolution (LR) seed PR (256×128), which a fine-tuned hybrid attention transformer (HAT) super-resolution (SR) stage upscales to a high-resolution (HR) PR of 1024×512. Decoupling the expensive generative step from the resolution step yields complete, full-arch PRs at diagnostic resolution on a single 47 GB GPU. The Fr'echet inception distance between 7243 real and synthetic HR images is 40.5. Inception scores were 2.68, 2.38, 2.90 and 2.98 for real HR, synthetic HR, real LR and synthetic LR images, respectively. Six clinical experts, each evaluating 100 synthetic and 100 real PRs under a time limit, distinguished real from synthetic images with an average accuracy of 68.5% (50% corresponds to random guessing), substantially closer to chance than reported for GAN-based studies. Project page: https://s4nyam.github.io/panodiff/