mlsanityData to 14 Oct 2026

Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution

arXiv 2110.07202 ↗First posted 14 Oct 2021cs.CV cs.AI math.OCcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a variational Bayesian algorithm (VBA) for image blind deconvolution. Our generic framework incorporates smoothness priors on the unknown blur/image and possible affine constraints (e.g., sum to one) on the blur kernel. One of our main contributions is the integration of VBA within a neural network paradigm, following an unrolling methodology. The proposed architecture is trained in a supervised fashion, which allows us to optimally set two key hyperparameters of the VBA model and lead to further improvements in terms of resulting visual quality. Various experiments involving grayscale/color images and diverse kernel shapes, are performed. The numerical examples illustrate the high performance of our approach when compared to state-of-the-art techniques based on optimization, Bayesian estimation, or deep learning.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 25 of its 66 references that are in the map. First posted on arXiv 14 Oct 2021.

Builds on

25 of 66 references.

References · 25

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2016Variational Inference: A Review for Statisticianscited by 1,472
  3. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  4. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  5. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
  6. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 367
  7. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 338
  8. 2020Deep Unfolding Network for Image Super-Resolutioncited by 254
  9. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 160
  10. 2019Neural Blind Deconvolution Using Deep Priorscited by 113
  11. 2020Kernel Operations on the GPU, with Autodiff, without Memory Overflowscited by 104
  12. 2020Learning Maximally Monotone Operators for Image Recoverycited by 62
13 more
  1. 2020Scalable Plug-and-Play ADMM with Convergence Guaranteescited by 50
  2. 2018Deep Neural Network Structures Solving Variational Inequalitiescited by 26
  3. 2018Deep Unfolding of a Proximal Interior Point Method for Image Restorationcited by 24
  4. 2021A Survey of Monte Carlo Methods for Parameter Estimationcited by 23
  5. 2018Scalable Bayesian uncertainty quantification in imaging inverse problems via convex optimizationcited by 22
  6. 2020Model Adaptation for Inverse Problems in Imagingcited by 21
  7. 2021Bilevel methods for image reconstructioncited by 20
  8. 2019An Algorithm Unrolling Approach to Deep Image Deblurringcited by 14
  9. 2016A Variational Bayesian Approach for Image Restoration. Application to Image Deblurring with Poisson-Gaussian Noisecited by 6
  10. 2021Deep Algorithm Unrolling for Biomedical Imagingcited by 6
  11. 2020Unfolding Neural Networks for Compressive Multichannel Blind Deconvolutioncited by 5
  12. 2018A Kernel Perspective for Regularizing Deep Neural Networkscited by 4
  13. 2021Inversion of Integral Models: a Neural Network Approachcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 1.

4 papers.

  1. 2023Block Coordinate Plug-and-Play Methods for Blind Inverse Problemscited by 8
  2. 2024A Generalized Tensor Formulation for Hyperspectral Image Super-Resolution Under General Spatial Blurringcited by 5
  3. 2024From Learning to Optimize to Learning Optimization Algorithmscited by 2
  4. 2026Leveraging Phase Information to Boost Unrolled Network Learning for Image Deblurringcited by 0