mlsanityData to 7 Oct 2026

Rethinking the CSC Model for Natural Images

arXiv 1909.05742 ↗First posted 12 Sep 2019eess.IV cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Sparse representation with respect to an overcomplete dictionary is often used when regularizing inverse problems in signal and image processing. In recent years, the Convolutional Sparse Coding (CSC) model, in which the dictionary consists of shift-invariant filters, has gained renewed interest. While this model has been successfully used in some image processing problems, it still falls behind traditional patch-based methods on simple tasks such as denoising. In this work we provide new insights regarding the CSC model and its capability to represent natural images, and suggest a Bayesian connection between this model and its patch-based ancestor. Armed with these observations, we suggest a novel feed-forward network that follows an MMSE approximation process to the CSC model, using strided convolutions. The performance of this supervised architecture is shown to be on par with state of the art methods while using much fewer parameters.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 6; 2023: 2; 2024: 3; 2025: 1; 2026: 1.

21 papers.

Sort:

By area:

  1. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  2. 2021A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restorationcited by 34
  3. 2021Stable and Interpretable Unrolled Dictionary Learningcited by 15
  4. 2023Deep Unfolding Convolutional Dictionary Model for Multi-Contrast MRI Super-resolution and Reconstructioncited by 6
  5. 2022Image Super-Resolution with Deep Dictionarycited by 5
  6. 2022Hybrid ISTA: Unfolding ISTA With Convergence Guarantees Using Free-Form Deep Neural Networkscited by 4
  7. 2022Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Networkcited by 4
  8. 2021On the convergence of group-sparse autoencoderscited by 3
  9. 2021CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicingcited by 2
  10. 2022Poisson2Sparse: Self-Supervised Poisson Denoising From a Single Imagecited by 2
  11. 2021Deep learning based dictionary learning and tomographic image reconstructioncited by 1
  12. 2022Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Priorcited by 1
9 more
  1. 2024Pivotal Auto-Encoder via Self-Normalizing ReLUcited by 1
  2. 2024Controlled Learning of Pointwise Nonlinearities in Neural-Network-Like Architecturescited by 1
  3. 2025Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizerscited by 1
  4. 2021CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learningcited by 0
  5. 2021Improved Image Generation via Sparse Modelingcited by 0
  6. 2021Learned Interpretable Residual Extragradient ISTA for Sparse Codingcited by 0
  7. 2022Learning unfolded networks with a cyclic group structurecited by 0
  8. 2023Learning Linear Groups in Neural Networkscited by 0
  9. 2026A deep dictionary network-based foundation model for ultra-low-dose CT denoisingcited by 0