mlsanityData to 14 Oct 2026

DEALing with Image Reconstruction: Deep Attentive Least Squares

arXiv 2502.04079 ↗First posted 6 Feb 2025eess.IV cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

State-of-the-art image reconstruction often relies on complex, highly parameterized deep architectures. We propose an alternative: a data-driven reconstruction method inspired by the classic Tikhonov regularization. Our approach iteratively refines intermediate reconstructions by solving a sequence of quadratic problems. These updates have two key components: (i) learned filters to extract salient image features, and (ii) an attention mechanism that locally adjusts the penalty of filter responses. Our method achieves performance on par with leading plug-and-play and learned regularizer approaches while offering interpretability, robustness, and convergent behavior. In effect, we bridge traditional regularization and deep learning with a principled reconstruction approach.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 6 Feb 2025.

Builds on

35 of 61 references.

References · 35

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  5. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  6. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  7. 2019Deep Equilibrium Modelscited by 615
  8. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  9. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  10. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 340
  11. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 307
  12. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 122
23 more
  1. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 108
  2. 2018Adversarial Regularizers in Inverse Problemscited by 103
  3. 2018Regularization by Denoising: Clarifications and New Interpretationscited by 103
  4. 2018NETT: Solving Inverse Problems with Deep Neural Networkscited by 89
  5. 2022Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularizationcited by 80
  6. 2020Learning Maximally Monotone Operators for Image Recoverycited by 62
  7. 2022A Neural-Network-Based Convex Regularizer for Inverse Problemscited by 41
  8. 2022Path Independent Equilibrium Models Can Better Exploit Test-Time Computationcited by 38
  9. 2020Convolutional Proximal Neural Networks and Plug-and-Play Algorithmscited by 36
  10. 2019Deep Graph-Convolutional Image Denoisingcited by 32
  11. 2023Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithmscited by 31
  12. 2022Improving Lipschitz-Constrained Neural Networks by Learning Activation Functionscited by 24
  13. 2022Stable Deep MRI Reconstruction using Generative Priorscited by 21
  14. 2014Insights into analysis operator learning: From patch-based sparse models to higher-order MRFscited by 18
  15. 2021Learning local regularization for variational image restorationcited by 16
  16. 2023Learning Regularization Parameter-Maps for Variational Image Reconstruction using Deep Neural Networks and Algorithm Unrollingcited by 14
  17. 2018Deep Graph Laplacian Regularization for Robust Denoising of Real Imagescited by 13
  18. 2023Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimizationcited by 10
  19. 2023Product of Gaussian Mixture Diffusion Modelscited by 6
  20. 2016Analytical aspects of spatially adapted total variation regularisationcited by 5
  21. 2024Stability of Data-Dependent Ridge-Regularization for Inverse Problemscited by 5
  22. 2016Learning optimal spatially-dependent regularization parameters in total variation image restorationcited by 4
  23. 2024Iteratively Refined Image Reconstruction with Learned Attentive Regularizerscited by 3

Built on by

Cited by year (2026 to 14 Oct)

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

6 papers.

  1. 2025Flower: A Flow-Matching Solver for Inverse Problemscited by 27
  2. 2025Learning Regularization Functionals for Inverse Problems: A Comparative Studycited by 15
  3. 2025Learning Spatially Adaptive ℓ1-Norms Weights for Convolutional Synthesis Regularizationcited by 2
  4. 2025Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoiserscited by 2
  5. 2026Learning spatially adaptive sparsity level maps for arbitrary convolutional dictionariescited by 1
  6. 2026Stabilizing Deep Reconstruction Operators with Contractive Anchoringcited by 0