mlsanityData to 7 Oct 2026

Bayesian Image Super-Resolution with Deep Modeling of Image Statistics

arXiv 2204.00623 ↗First posted 31 Mar 2022eess.IV cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Modeling statistics of image priors is useful for image super-resolution, but little attention has been paid from the massive works of deep learning-based methods. In this work, we propose a Bayesian image restoration framework, where natural image statistics are modeled with the combination of smoothness and sparsity priors. Concretely, firstly we consider an ideal image as the sum of a smoothness component and a sparsity residual, and model real image degradation including blurring, downscaling, and noise corruption. Then, we develop a variational Bayesian approach to infer their posteriors. Finally, we implement the variational approach for single image super-resolution (SISR) using deep neural networks, and propose an unsupervised training strategy. The experiments on three image restoration tasks, textiti.e., ideal SISR, realistic SISR, and real-world SISR, demonstrate that our method has superior model generalizability against varying noise levels and degradation kernels and is effective in unsupervised SISR. The code and resulting models are released via urlhttps://zmiclab.github.io/projects.html.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 37 of its 80 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

37 of 80 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  7. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  8. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  9. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  10. 2017Deep Image Priorcited by 1,097
  11. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  12. 2020Pre-Trained Image Processing Transformercited by 891
25 more
  1. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  2. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  3. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  4. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  5. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  6. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  7. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  8. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  9. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  10. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  11. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  12. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  13. 2019Blind Super-Resolution Kernel Estimation using an Internal-GANcited by 175
  14. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
  15. 2019Variational Denoising Network: Toward Blind Noise Modeling and Removalcited by 117
  16. 2020Meta-Transfer Learning for Zero-Shot Super-Resolutioncited by 116
  17. 2018To learn image super-resolution, use a GAN to learn how to do image degradation firstcited by 94
  18. 2018Denoising Prior Driven Deep Neural Network for Image Restorationcited by 80
  19. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  20. 2020Unpaired Image Super-Resolution using Pseudo-Supervisioncited by 67
  21. 2018Wide Activation for Efficient and Accurate Image Super-Resolutioncited by 64
  22. 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
  23. 2017Deep Mean-Shift Priors for Image Restorationcited by 34
  24. 2019Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learningcited by 31
  25. 2020Patch-based Non-Local Bayesian Networks for Blind Confocal Microscopy Denoisingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 3; 2026: 1.

11 papers.

  1. 2023BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizabilitycited by 42
  2. 2022Image Super-resolution with An Enhanced Group Convolutional Neural Networkcited by 7
  3. 2024A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurringcited by 5
  4. 2023Variational Bayes image restoration with compressive autoencoderscited by 4
  5. 2024Deep priors for satellite image restoration with accurate uncertaintiescited by 1
  6. 2025BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolutioncited by 1
  7. 2023Combination of Single and Multi-frame Image Super-resolution: An Analytical Perspectivecited by 0
  8. 2024A Single-Frame and Multi-Frame Cascaded Image Super-Resolution Methodcited by 0
  9. 2025MambaX: Image Super-Resolution with State Predictive Controlcited by 0
  10. 2025Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalizationcited by 0
  11. 2026Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detectioncited by 0