mlsanityData to 7 Oct 2026

HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training

arXiv 2601.01228 ↗First posted 3 Jan 2026cs.CV cs.NA math.NAcited by 0

Not on the map. Why?

Abstract (arXiv)

Solving image reconstruction problems of the form (A x = y) remains challenging due to ill-posedness and the lack of large-scale supervised datasets. Deep Equilibrium (DEQ) models have been used successfully but typically require supervised pairs ((x,y)). In many practical settings, only measurements (y) are available. We introduce HyDRA (Hybrid Denoising Regularization Adaptation), a measurement-only framework for DEQ training that combines measurement consistency with an adaptive denoising regularization term, together with a data-driven early stopping criterion. Experiments on sparse-view CT demonstrate competitive reconstruction quality and fast inference.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 44 references that are in the map. First posted on arXiv 3 Jan 2026.

Builds on

26 of 44 references.

References · 26

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2017Deep Image Priorcited by 1,097
  3. 2019Deep Equilibrium Modelscited by 603
  4. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  5. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  6. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  7. 2017Learned Primal-dual Reconstructioncited by 251
  8. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 231
  9. 2017Solving ill-posed inverse problems using iterative deep neural networkscited by 145
  10. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
  11. 2021JFB: Jacobian-Free Backpropagation for Implicit Networkscited by 84
  12. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
14 more
  1. 2017One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Modelscited by 67
  2. 2021Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurementscited by 56
  3. 2019A Bayesian Perspective on the Deep Image Priorcited by 52
  4. 2022A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noisecited by 29
  5. 2019Deep Decomposition Learning for Inverse Imaging Problemscited by 25
  6. 2016Regularized Nonlinear Accelerationcited by 18
  7. 2024UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimatecited by 16
  8. 2020Neural Network-based Reconstruction in Compressed Sensing MRI Without Fully-sampled Training Datacited by 14
  9. 2019Unsupervised Deep Basis Pursuit: Learning inverse problems without ground-truth datacited by 10
  10. 2024Sparse2Inverse: Self-supervised inversion of sparse-view CT datacited by 8
  11. 2025Noisier2Inverse: Self-Supervised Learning for Image Reconstruction with Correlated Noisecited by 5
  12. 2025Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Datacited by 5
  13. 2025TomoSelfDEQ: Self-Supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstructioncited by 3
  14. 2025Unsupervised Deep Learning for Inverse Problems in Computed Tomographycited by 1

Built on by

Not cited yet.