mlsanityData to 7 Oct 2026

Dynamic Attention-Guided Diffusion for Image Super-Resolution

arXiv 2308.07977 ↗First posted 15 Aug 2023cs.CV cs.AI cs.LGcited by 10

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

Abstract (arXiv)

Diffusion models in image Super-Resolution (SR) treat all image regions uniformly, which risks compromising the overall image quality by potentially introducing artifacts during denoising of less-complex regions. To address this, we propose ``You Only Diffuse Areas'' (YODA), a dynamic attention-guided diffusion process for image SR. YODA selectively focuses on spatial regions defined by attention maps derived from the low-resolution images and the current denoising time step. This time-dependent targeting enables a more efficient conversion to high-resolution outputs by focusing on areas that benefit the most from the iterative refinement process, i.e., detail-rich objects. We empirically validate YODA by extending leading diffusion-based methods SR3, DiffBIR, and SRDiff. Our experiments demonstrate new state-of-the-art performances in face and general SR tasks across PSNR, SSIM, and LPIPS metrics. As a side effect, we find that YODA reduces color shift issues and stabilizes training with small batches.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 42 of its 63 references that are in the map. First posted on arXiv 15 Aug 2023.

Builds on

42 of 63 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  2. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration20 Mar
  3. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  4. 2022Denoising Diffusion Restoration Models27 Jan
  5. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction9 Dec
  6. 2021Deblurring via Stochastic Refinement5 Dec
  7. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  12. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
23 more
  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  2. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  3. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  4. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  5. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  6. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  7. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  8. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 275
  9. 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 214
  10. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  11. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  12. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  13. 2022MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusioncited by 66
  14. 2019Densely Residual Laplacian Super-Resolutioncited by 57
  15. 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
  16. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  17. 2019Path-Restore: Learning Network Path Selection for Image Restorationcited by 39
  18. 2016RAISR: Rapid and Accurate Image Super Resolutioncited by 27
  19. 2020Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorizationcited by 23
  20. 2022Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advancescited by 21
  21. 2022Adaptive Patch Exiting for Scalable Single Image Super-Resolutioncited by 16
  22. 2023DWA: Differential Wavelet Amplifier for Image Super-Resolutioncited by 4
  23. 2023PartDiff: Image Super-resolution with Partial Diffusion Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 6; 2026: 1.

10 papers.

  1. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  2. 2023ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separationcited by 37
  3. 2025A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advancescited by 28
  4. 2025Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesiscited by 6
  5. 2025VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Resultscited by 5
  6. 2025Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessmentcited by 2
  7. 2026R3D: Regional-guided Residual Radar Diffusioncited by 2
  8. 2024Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolutioncited by 1
  9. 2025SkipSR: Faster Super Resolution with Token Skippingcited by 1
  10. 2025HDW-SR: High-Frequency Guided Diffusion Model based on Wavelet Decomposition for Image Super-Resolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Accelerating Diffusion-based Super-Resolution with Dynamic Time-Spatial Sampling
  2. 2024FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion
  3. 2025Local-Global Context-Aware and Structure-Preserving Image Super-Resolution
  4. 2024You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
  5. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
  6. 2025Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution
  7. 2025GuideSR: Rethinking Guidance for One-Step High-Fidelity Diffusion-Based Super-Resolution
  8. 2026Degradation-Aware and Structure-Preserving Diffusion for Real-World Image Super-Resolution