mlsanityData to 7 Oct 2026

A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

arXiv 2210.13389 ↗First posted 24 Oct 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

In image recovery problems, one seeks to infer an image from distorted, incomplete, and/or noise-corrupted measurements. Such problems arise in magnetic resonance imaging (MRI), computed tomography, deblurring, super-resolution, inpainting, phase retrieval, image-to-image translation, and other applications. Given a training set of signal/measurement pairs, we seek to do more than just produce one good image estimate. Rather, we aim to rapidly and accurately sample from the posterior distribution. To do this, we propose a regularized conditional Wasserstein GAN that generates dozens of high-quality posterior samples per second. Our regularization comprises an ℓ1 penalty and an adaptively weighted standard-deviation reward. Using quantitative evaluation metrics like conditional Fr'echet inception distance, we demonstrate that our method produces state-of-the-art posterior samples in both multicoil MRI and large-scale inpainting applications. The code for our model can be found here: https://github.com/matt-bendel/rcGAN

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

36 of 52 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2017Improved Training of Wasserstein GANscited by 2,223
  10. 2014Conditional Generative Adversarial Netscited by 2,152
  11. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
24 more
  1. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  2. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  3. 2017The Perception-Distortion Tradeoffcited by 582
  4. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  5. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  6. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  7. 2021Large Scale Image Completion via Co-Modulated Generative Adversarial Networkscited by 219
  8. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  9. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  10. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  11. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  12. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  13. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  14. 2016Amortised MAP Inference for Image Super-resolutioncited by 68
  15. 2020Improved Consistency Regularization for GANscited by 67
  16. 2018Deep Bayesian Inversioncited by 60
  17. 2020Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imagingcited by 57
  18. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  19. 2021High Perceptual Quality Image Denoising with a Posterior Sampling CGANcited by 33
  20. 2014On the folded normal distributioncited by 31
  21. 2019Deep Decomposition Learning for Inverse Imaging Problemscited by 25
  22. 2021Conditional Frechet Inception Distancecited by 16
  23. 2019Structure Preserving Compressive Sensing MRI Reconstruction using Generative Adversarial Networkscited by 8
  24. 2022Technical Report (v1.0)--Pseudo-random Cartesian Sampling for Dynamic MRIcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 2.

9 papers.

  1. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Datacited by 32
  2. 2024Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restorationcited by 32
  3. 2025Measurement Score-Based Diffusion Modelcited by 7
  4. 2025Learning few-step posterior samplers by unfolding and distillation of diffusion modelscited by 5
  5. 2026Self-Supervised Learning from Noisy and Incomplete Datacited by 5
  6. 2024Hierarchical Uncertainty Exploration via Feedforward Posterior Treescited by 4
  7. 2025Conditional Flow Matching for Bayesian Posterior Inferencecited by 3
  8. 2025Bayesian model selection and misspecification testing in imaging inverse problems only from noisy and partial measurementscited by 0
  9. 2026Deep unfolding of MCMC kernels: scalable, modular & explainable GANs for high-dimensional posterior samplingcited by 0