mlsanityData to 7 Oct 2026

DREAM: Diffusion Rectification and Estimation-Adaptive Models

arXiv 2312.00210 ↗First posted 30 Nov 2023cs.CV cs.AIcited by 12

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

Abstract (arXiv)

We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in diffusion models. DREAM features two components: diffusion rectification, which adjusts training to reflect the sampling process, and estimation adaptation, which balances perception against distortion. When applied to image super-resolution (SR), DREAM adeptly navigates the tradeoff between minimizing distortion and preserving high image quality. Experiments demonstrate DREAM's superiority over standard diffusion-based SR methods, showing a 2 to 3× faster training convergence and a 10 to 20× reduction in sampling steps to achieve comparable results. We hope DREAM will inspire a rethinking of diffusion model training paradigms.

Key facts. Cited by 12 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 55 of its 69 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

55 of 69 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting23 Jul
  2. 2023Implicit Diffusion Models for Continuous Super-Resolution29 Mar
  3. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 52

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2022Generative Adversarial Networkscited by 5,603
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  10. 2017Neural Discrete Representation Learningcited by 4,650
  11. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  12. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
38 more
  1. 2016Density estimation using Real NVPcited by 2,029
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  7. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  10. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  11. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  12. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  13. 2016Pixel Recurrent Neural Networkscited by 814
  14. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  15. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  16. 2017The Perception-Distortion Tradeoffcited by 582
  17. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 550
  18. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  19. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  20. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  21. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  22. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  23. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  24. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  25. 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
  26. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  27. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  28. 2021Step-unrolled Denoising Autoencoders for Text Generationcited by 102
  29. 2023Elucidating the Exposure Bias in Diffusion Modelscited by 98
  30. 2023Input Perturbation Reduces Exposure Bias in Diffusion Modelscited by 88
  31. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  32. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  33. 2023Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Stepscited by 71
  34. 2019Densely Residual Laplacian Super-Resolutioncited by 57
  35. 2021CDFI: Compression-Driven Network Design for Frame Interpolationcited by 55
  36. 2022RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolutioncited by 44
  37. 2023Exploiting the Signal-Leak Bias in Diffusion Modelscited by 36
  38. 2019Natural and Realistic Single Image Super-Resolution with Explicit Natural Manifold Discriminationcited by 32

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 3; 2026: 3.

12 papers.

  1. 2024FORA: Fast-Forward Caching in Diffusion Transformer Accelerationcited by 127
  2. 2024Learning Flow Fields in Attention for Controllable Person Image Generationcited by 27
  3. 2024HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruningcited by 4
  4. 2025Learning Where and What to Restore for Composite Image Restorationcited by 4
  5. 2025How I Met Your Bias: Investigating Bias Amplification in Diffusion Modelscited by 4
  6. 2026DODO: Discrete OCR Diffusion Modelscited by 2
  7. 2024Mitigating Data Consistency Induced Discrepancy in Cascaded Diffusion Models for Sparse-view CT Reconstructioncited by 1
  8. 2024S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editingcited by 1
  9. 2024AdaContour: Adaptive Contour Descriptor with Hierarchical Representationcited by 0
  10. 2025Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoisecited by 0
  11. 2026BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Offcited by 0
  12. 2026Structure-Guided Diffusion Model for EEG-Based Visual Cognition Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models, Image Super-Resolution And Everything: A Survey
  2. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution
  3. 2025One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
  4. 2026Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution
  5. 2026Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution
  6. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation
  7. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
  8. 2026Perceptually Regularized Diffusion Model for Image Super-Resolution