mlsanityData to 14 Oct 2026

The Perception-Distortion Tradeoff

arXiv 1711.06077 ↗First posted 16 Nov 2017cs.CVcited by 587

Not on the map. Why?

Cited by 200 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image restoration algorithms are typically evaluated by some distortion measure (e.g. PSNR, SSIM, IFC, VIF) or by human opinion scores that quantify perceived perceptual quality. In this paper, we prove mathematically that distortion and perceptual quality are at odds with each other. Specifically, we study the optimal probability for correctly discriminating the outputs of an image restoration algorithm from real images. We show that as the mean distortion decreases, this probability must increase (indicating worse perceptual quality). As opposed to the common belief, this result holds true for any distortion measure, and is not only a problem of the PSNR or SSIM criteria. We also show that generative-adversarial-nets (GANs) provide a principled way to approach the perception-distortion bound. This constitutes theoretical support to their observed success in low-level vision tasks. Based on our analysis, we propose a new methodology for evaluating image restoration methods, and use it to perform an extensive comparison between recent super-resolution algorithms.

Key facts. Cited by 587 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 59; 2022: 65; 2023: 82; 2024: 88; 2025: 141; 2026: 152.

587 papers.

Sort:

By area:

  1. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  2. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  3. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 970
  4. 2022Denoising Diffusion Restoration Modelscited by 963
  5. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  6. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
  7. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 529
  8. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 522
  9. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  10. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 365
  11. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  12. 2021Deblurring via Stochastic Refinementcited by 249
38 more
  1. 2022Diffusion Probabilistic Modeling for Video Generationcited by 238
  2. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 220
  3. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 205
  4. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  5. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  6. 2024A Survey on Diffusion Models for Inverse Problemscited by 180
  7. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 165
  8. 2022FILM: Frame Interpolation for Large Motioncited by 153
  9. 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
  10. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 147
  11. 2023Dual Aggregation Transformer for Image Super-Resolutioncited by 124
  12. 2022VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decodercited by 116
  13. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  14. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
  15. 2021Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEcited by 106
  16. 2023Towards image compression with perfect realism at ultra-low bitratescited by 103
  17. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 100
  18. 2024PnP-Flow: Plug-and-Play Image Restoration with Flow Matchingcited by 97
  19. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 97
  20. 2022Deep Image Deblurring: A Surveycited by 94
  21. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 94
  22. 2022Lossy Compression with Gaussian Diffusioncited by 90
  23. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 87
  24. 2022An Introduction to Neural Data Compressioncited by 79
  25. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 77
  26. 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
  27. 2023Prompt-tuning latent diffusion models for inverse problemscited by 70
  28. 2022MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusioncited by 67
  29. 2022MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-raycited by 66
  30. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problemscited by 66
  31. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  32. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  33. 2024Learning Diffusion Priors from Observations by Expectation Maximizationcited by 61
  34. 2022Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problemscited by 60
  35. 2022Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Networkcited by 57
  36. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  37. 2023High-Fidelity Image Compression with Score-based Generative Modelscited by 54
  38. 2024Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matchingcited by 53

50 most cited of 587 All 587 (JSON)