Data to 14 Oct 2026

Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors

arXiv 2409.17058 ↗First posted 25 Sep 2024cs.CVcited by 69

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Diffusion-based image super-resolution (SR) methods have achieved remarkable success by leveraging large pre-trained text-to-image diffusion models as priors. However, these methods still face two challenges: the requirement for dozens of sampling steps to achieve satisfactory results, which limits efficiency in real scenarios, and the neglect of degradation models, which are critical auxiliary information in solving the SR problem. In this work, we introduced a novel one-step SR model, which significantly addresses the efficiency issue of diffusion-based SR methods. Unlike existing fine-tuning strategies, we designed a degradation-guided Low-Rank Adaptation (LoRA) module specifically for SR, which corrects the model parameters based on the pre-estimated degradation information from low-resolution images. This module not only facilitates a powerful data-dependent or degradation-dependent SR model but also preserves the generative prior of the pre-trained diffusion model as much as possible. Furthermore, we tailor a novel training pipeline by introducing an online negative sample generation strategy. Combined with the classifier-free guidance strategy during inference, it largely improves the perceptual quality of the super-resolution results. Extensive experiments have demonstrated the superior efficiency and effectiveness of the proposed model compared to recent state-of-the-art methods.

Key facts. Cited by 69 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 51 of its 78 references that are in the map. First posted on arXiv 25 Sep 2024.

Builds on

51 of 78 references.

Closest ancestors · 13

Same direction, newest first

1 more

2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction9 Dec

Other references · 38

2020Denoising Diffusion Probabilistic Modelscited by 21,076
2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694

26 more

2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
2021Image Super-Resolution via Iterative Refinementcited by 1,511
2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 811
2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 371
2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 279
2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 228
2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
2024One-Step Image Translation with Text-to-Image Modelscited by 116
2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 100
2021Ensembling Off-the-shelf Models for GAN Trainingcited by 86
2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
2022MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolutioncited by 33
2023Image Super-Resolution with Text Prompt Diffusioncited by 23
2020Deep Variational Network Toward Blind Image Restorationcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 23; 2026: 41.

69 papers.

Sort:

By area:

2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 86
2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 53
2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 52
2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 50
2025Harnessing Diffusion-Yielded Score Priors for Image Restorationcited by 36
2025StableCodec: Taming One-Step Diffusion for Extreme Image Compressioncited by 33
2025Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Trainingcited by 21
2025Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignmentcited by 8
2025PocketSR: The Super-Resolution Expert in Your Pocket Mobilescited by 8
2025Time-Aware One Step Diffusion Network for Real-World Image Super-Resolutioncited by 7
2025Ultra-Low Bitrate Perceptual Image Compression with Shallow Encodercited by 7
2025Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusioncited by 7

38 more

50 most cited of 69 All 69 (JSON)

Similar, not cited

Close in wording, no citation either way