# Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild

arXiv: https://arxiv.org/abs/2302.07864 · HTML: https://mlsanity.com/paper/2302.07864/

## Key facts

- Cited by 46 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 37 of its 46 references that are in the map.
- First posted on arXiv 15 Feb 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 37)

- [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)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [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)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Deblurring via Stochastic Refinement](https://mlsanity.com/paper/2112.02475/) (2021)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [Unsupervised Degradation Representation Learning for Blind Super-Resolution](https://mlsanity.com/paper/2104.00416/) (2021)
- [FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors](https://mlsanity.com/paper/1711.10703/) (2017)

## Built on by (most cited first, 30 of 46)

- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution](https://mlsanity.com/paper/2312.06640/) (2023)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [Video Interpolation with Diffusion Models](https://mlsanity.com/paper/2404.01203/) (2024)
- [AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation](https://mlsanity.com/paper/2404.01717/) (2024)
- [MarDini: Masked Autoregressive Diffusion for Video Generation at Scale](https://mlsanity.com/paper/2410.20280/) (2024)
- [XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution](https://mlsanity.com/paper/2403.05049/) (2024)
- [Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices](https://mlsanity.com/paper/2410.11795/) (2024)
- [Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Images](https://mlsanity.com/paper/2308.16582/) (2023)
- [Conditional Image Synthesis with Diffusion Models: A Survey](https://mlsanity.com/paper/2409.19365/) (2024)
- [You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation](https://mlsanity.com/paper/2401.17258/) (2024)
- [Super-NeRF: View-consistent Detail Generation for NeRF super-resolution](https://mlsanity.com/paper/2304.13518/) (2023)
- [Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach](https://mlsanity.com/paper/2306.01433/) (2023)
- [Bigger is not Always Better: Scaling Properties of Latent Diffusion Models](https://mlsanity.com/paper/2404.01367/) (2024)
- [Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models](https://mlsanity.com/paper/2404.09732/) (2024)
- [EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation](https://mlsanity.com/paper/2503.15831/) (2025)
- [Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models](https://mlsanity.com/paper/2311.15908/) (2023)
- [Automated data processing and feature engineering for deep learning and big data applications: a survey](https://mlsanity.com/paper/2403.11395/) (2024)
- [Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach](https://mlsanity.com/paper/2310.12004/) (2023)
- [CoBIT: A Contrastive Bi-directional Image-Text Generation Model](https://mlsanity.com/paper/2303.13455/) (2023)
- [Squeezing Large-Scale Diffusion Models for Mobile](https://mlsanity.com/paper/2307.01193/) (2023)
- [NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study](https://mlsanity.com/paper/2504.15003/) (2025)
- [AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution](https://mlsanity.com/paper/2410.17752/) (2024)
- [Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution](https://mlsanity.com/paper/2305.15357/) (2023)
- [Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning](https://mlsanity.com/paper/2412.06978/) (2024)
- [Text-Aware Image Restoration with Diffusion Models](https://mlsanity.com/paper/2506.09993/) (2025)
- [DWA: Differential Wavelet Amplifier for Image Super-Resolution](https://mlsanity.com/paper/2307.04593/) (2023)
- [Structure-guided Diffusion Transformer for Low-Light Image Enhancement](https://mlsanity.com/paper/2504.15054/) (2025)
- [AniRes2D: Anisotropic Residual-enhanced Diffusion for 2D MR Super-Resolution](https://mlsanity.com/paper/2312.04385/) (2023)
- [Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution](https://mlsanity.com/paper/2402.18929/) (2024)

## Abstract (arXiv)

Diffusion models have shown promising results on single-image super-resolution and other image- to-image translation tasks. Despite this success, they have not outperformed state-of-the-art GAN models on the more challenging blind super-resolution task, where the input images are out of distribution, with unknown degradations. This paper introduces SR3+, a diffusion-based model for blind super-resolution, establishing a new state-of-the-art. To this end, we advocate self-supervised training with a combination of composite, parameterized degradations for self-supervised training, and noise-conditioing augmentation during training and testing. With these innovations, a large-scale convolutional architecture, and large-scale datasets, SR3+ greatly outperforms SR3. It outperforms Real-ESRGAN when trained on the same data, with a DRealSR FID score of 36.82 vs. 37.22, which further improves to FID of 32.37 with larger models, and further still with larger training sets.