mlsanityData to 7 Oct 2026

SRFlow: Learning the Super-Resolution Space with Normalizing Flow

arXiv 2006.14200 ↗First posted 25 Jun 2020cs.CV eess.IVcited by 209

Not on the map. Why?

Cited by 52 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Super-resolution is an ill-posed problem, since it allows for multiple predictions for a given low-resolution image. This fundamental fact is largely ignored by state-of-the-art deep learning based approaches. These methods instead train a deterministic mapping using combinations of reconstruction and adversarial losses. In this work, we therefore propose SRFlow: a normalizing flow based super-resolution method capable of learning the conditional distribution of the output given the low-resolution input. Our model is trained in a principled manner using a single loss, namely the negative log-likelihood. SRFlow therefore directly accounts for the ill-posed nature of the problem, and learns to predict diverse photo-realistic high-resolution images. Moreover, we utilize the strong image posterior learned by SRFlow to design flexible image manipulation techniques, capable of enhancing super-resolved images by, e.g., transferring content from other images. We perform extensive experiments on faces, as well as on super-resolution in general. SRFlow outperforms state-of-the-art GAN-based approaches in terms of both PSNR and perceptual quality metrics, while allowing for diversity through the exploration of the space of super-resolved solutions.

Key facts. Cited by 209 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 49; 2022: 44; 2023: 43; 2024: 44; 2025: 17; 2026: 12.

209 papers.

Sort:

By area:

  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  3. 2021GAN Inversion: A Surveycited by 366
  4. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  5. 2021Deblurring via Stochastic Refinementcited by 248
  6. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  7. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  8. 2021Low-Light Image Enhancement with Normalizing Flowcited by 184
  9. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182
  10. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  11. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 102
  12. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 102
38 more
  1. 2021Deep Burst Super-Resolutioncited by 83
  2. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
  3. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  4. 2021Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescalingcited by 73
  5. 2021Fourier Space Losses for Efficient Perceptual Image Super-Resolutioncited by 72
  6. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  7. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  8. 2022Towards Blind Watermarking: Combining Invertible and Non-invertible Mechanismscited by 61
  9. 2022Conditional Simulation Using Diffusion Schr"odinger Bridgescited by 58
  10. 2024Towards Realistic Data Generation for Real-World Super-Resolutioncited by 56
  11. 2023ResDiff: Combining CNN and Diffusion Model for Image Super-Resolutioncited by 53
  12. 2021A Theory of the Distortion-Perception Tradeoff in Wasserstein Spacecited by 52
  13. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  14. 2022Deep Constrained Least Squares for Blind Image Super-Resolutioncited by 47
  15. 2023WaveDM: Wavelet-Based Diffusion Models for Image Restorationcited by 46
  16. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  17. 2021iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesiscited by 42
  18. 2022Do better ImageNet classifiers assess perceptual similarity better?cited by 34
  19. 2023Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolutioncited by 34
  20. 2023Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Modelscited by 33
  21. 2024GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrievalcited by 33
  22. 2021DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flowscited by 30
  23. 2022Hard-Constrained Deep Learning for Climate Downscalingcited by 29
  24. 2022DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Modelcited by 29
  25. 2023ExposureDiffusion: Learning to Expose for Low-light Image Enhancementcited by 29
  26. 2021SRWarp: Generalized Image Super-Resolution under Arbitrary Transformationcited by 26
  27. 2021COMISR: Compression-Informed Video Super-Resolutioncited by 26
  28. 2023Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernelcited by 25
  29. 2022Collapse by Conditioning: Training Class-conditional GANs with Limited Datacited by 24
  30. 2024Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challengescited by 24
  31. 2024Perception-Oriented Video Frame Interpolation via Asymmetric Blendingcited by 23
  32. 2021NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Resultscited by 22
  33. 2022PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularizationcited by 22
  34. 2024DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRFcited by 22
  35. 2024SuperGaussian: Repurposing Video Models for 3D Super Resolutioncited by 22
  36. 2022Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimationcited by 21
  37. 2023CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolutioncited by 21
  38. 2023Super-NeRF: View-consistent Detail Generation for NeRF super-resolutioncited by 21

50 most cited of 209 All 209 (JSON)