# Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach arXiv: https://arxiv.org/abs/2303.06994 ยท HTML: https://mlsanity.com/paper/2303.06994/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. - Builds on 46 of its 56 references that are in the map. - First posted on arXiv 13 Mar 2023. ## Placed in - Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/) ## Builds on (most cited first, 30 of 46) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [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) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015) - [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021) - [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017) - [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022) - [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022) - [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022) - [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021) - [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019) - [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017) - [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015) - [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016) - [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022) - [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021) - [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018) - [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014) - [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021) - [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016) - [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021) - [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017) - [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019) - [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021) - [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018) - [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020) - [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022) ## Built on by (most cited first, 11 of 11) - [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023) - [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023) - [CoSeR: Bridging Image and Language for Cognitive Super-Resolution](https://mlsanity.com/paper/2311.16512/) (2023) - [Towards Realistic Data Generation for Real-World Super-Resolution](https://mlsanity.com/paper/2406.07255/) (2024) - [DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolution](https://mlsanity.com/paper/2406.16477/) (2024) - [DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement](https://mlsanity.com/paper/2308.09279/) (2023) - [Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution](https://mlsanity.com/paper/2402.18929/) (2024) - [Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal](https://mlsanity.com/paper/2511.17353/) (2025) - [Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning](https://mlsanity.com/paper/2603.04870/) (2026) - [Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling](https://mlsanity.com/paper/2508.07214/) (2025) - [DiffusionXRay: A Diffusion and GAN-Based Approach for Enhancing Digitally Reconstructed Chest Radiographs](https://mlsanity.com/paper/2603.01686/) (2026) ## Abstract (arXiv) In supervised image restoration tasks, one key issue is how to obtain the aligned high-quality (HQ) and low-quality (LQ) training image pairs. Unfortunately, such HQ-LQ training pairs are hard to capture in practice, and hard to synthesize due to the complex unknown degradation in the wild. While several sophisticated degradation models have been manually designed to synthesize LQ images from their HQ counterparts, the distribution gap between the synthesized and real-world LQ images remains large. We propose a new approach to synthesizing realistic image restoration training pairs using the emerging denoising diffusion probabilistic model (DDPM). First, we train a DDPM, which could convert a noisy input into the desired LQ image, with a large amount of collected LQ images, which define the target data distribution. Then, for a given HQ image, we synthesize an initial LQ image by using an off-the-shelf degradation model, and iteratively add proper Gaussian noises to it. Finally, we denoise the noisy LQ image using the pre-trained DDPM to obtain the final LQ image, which falls into the target distribution of real-world LQ images. Thanks to the strong capability of DDPM in distribution approximation, the synthesized HQ-LQ image pairs can be used to train robust models for real-world image restoration tasks, such as blind face image restoration and blind image super-resolution. Experiments demonstrated the superiority of our proposed approach to existing degradation models. Code and data will be released.