mlsanityData to 7 Oct 2026

Unrolled Optimization with Deep Priors

arXiv 1705.08041 ↗First posted 22 May 2017cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

A broad class of problems at the core of computational imaging, sensing, and low-level computer vision reduces to the inverse problem of extracting latent images that follow a prior distribution, from measurements taken under a known physical image formation model. Traditionally, hand-crafted priors along with iterative optimization methods have been used to solve such problems. In this paper we present unrolled optimization with deep priors, a principled framework for infusing knowledge of the image formation into deep networks that solve inverse problems in imaging, inspired by classical iterative methods. We show that instances of the framework outperform the state-of-the-art by a substantial margin for a wide variety of imaging problems, such as denoising, deblurring, and compressed sensing magnetic resonance imaging (MRI). Moreover, we conduct experiments that explain how the framework is best used and why it outperforms previous methods.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 9; 2023: 3; 2024: 6; 2025: 3; 2026: 1.

40 papers.

Sort:

  1. 2021Learning to Optimize: A Primer and A Benchmarkcited by 206
  2. 2021Bayesian imaging using Plug & Play priors: when Langevin meets Tweediecited by 96
  3. 2022SKM-TEA: A Dataset for Accelerated MRI Reconstruction with Dense Image Labels for Quantitative Clinical Evaluationcited by 42
  4. 2021AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysiscited by 38
  5. 2023Learning to Warm-Start Fixed-Point Optimization Algorithmscited by 32
  6. 2021Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Priorcited by 24
  7. 2022Alternating Differentiation for Optimization Layerscited by 22
  8. 2021Efficient differentiable quadratic programming layers: an ADMM approachcited by 19
  9. 2021Feasibility-based Fixed Point Networkscited by 17
  10. 2021Joint inference and input optimization in equilibrium networkscited by 15
  11. 2022On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descentcited by 14
  12. 2022Uncertainty Quantification for Deep Unrolling-Based Computational Imagingcited by 10
28 more
  1. 2022Graph-based Neural Acceleration for Nonnegative Matrix Factorizationcited by 9
  2. 2021Preconditioned Plug-and-Play ADMM with Locally Adjustable Denoiser for Image Restorationcited by 7
  3. 2022PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descentcited by 7
  4. 2021MAC-ReconNet: A Multiple Acquisition Context based Convolutional Neural Network for MR Image Reconstruction using Dynamic Weight Predictioncited by 6
  5. 2021Memory-efficient Learning for High-Dimensional MRI Reconstructioncited by 5
  6. 2024Data-Driven Performance Guarantees for Classical and Learned Optimizerscited by 5
  7. 2025Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizerscited by 4
  8. 2021Phase Retrieval using Expectation Consistent Signal Recovery Algorithm based on Hypernetworkcited by 3
  9. 2021Deep Unrolled Network for Video Super-Resolutioncited by 3
  10. 2021FourierNets enable the design of highly non-local optical encoders for computational imagingcited by 3
  11. 2021Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectivescited by 3
  12. 2022Training Adaptive Reconstruction Networks for Blind Inverse Problemscited by 3
  13. 2024Unsupervised Training of Convex Regularizers using Maximum Likelihood Estimationcited by 3
  14. 2021Procedural Kernel Networkscited by 2
  15. 2022Deep learning-based reconstruction of highly accelerated 3D MRIcited by 2
  16. 2023A Compound Gaussian Least Squares Algorithm and Unrolled Network for Linear Inverse Problemscited by 2
  17. 2023TpopT: Efficient Trainable Template Optimization on Low-Dimensional Manifoldscited by 2
  18. 2024Deep Learning-based Accelerated MR Cholangiopancreatography without Fully-sampled Datacited by 2
  19. 2024WARP-LCA: Efficient Convolutional Sparse Coding with Locally Competitive Algorithmcited by 2
  20. 2021Joint Optimization of Hadamard Sensing and Reconstruction in Compressed Sensing Fluorescence Microscopycited by 1
  21. 2022Video Restoration with a Deep Plug-and-Play Priorcited by 1
  22. 2024On Generalization Bounds for Deep Compound Gaussian Neural Networkscited by 1
  23. 2025Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problemscited by 1
  24. 2021Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensingcited by 0
  25. 2021Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translationcited by 0
  26. 2024Low-Rank Representations Meets Deep Unfolding: A Generalized and Interpretable Network for Hyperspectral Anomaly Detectioncited by 0
  27. 2025Understanding Benefits and Pitfalls of Current Methods for the Segmentation of Undersampled MRI Datacited by 0
  28. 2026Majorization-Minimization Networks for Inverse Problems: An Application to EEG Imagingcited by 0