Learning of Patch-Based Smooth-Plus-Sparse Models for Image Reconstruction
Not on the map. Why?
Abstract (arXiv)
We aim at the solution of inverse problems in imaging, by combining a penalized sparse representation of image patches with an unconstrained smooth one. This allows for a straightforward interpretation of the reconstruction. We formulate the optimization as a bilevel problem. The inner problem deploys classical algorithms while the outer problem optimizes the dictionary and the regularizer parameters through supervised learning. The process is carried out via implicit differentiation and gradient-based optimization. We evaluate our method for denoising, super-resolution, and compressed-sensing magnetic-resonance imaging. We compare it to other classical models as well as deep-learning-based methods and show that it always outperforms the former and also the latter in some instances.
Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 20 of its 50 references that are in the map. First posted on arXiv 17 Dec 2024.
Builds on
20 of 50 references.
References · 20
- 2019Deep Equilibrium Modelscited by 606
- 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 469
- 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 467
- 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
- 2022Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularizationcited by 79
- 2019Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learningcited by 60
- 2016A survey of sparse representation: algorithms and applicationscited by 58
- 2017Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problemscited by 40
- 2022A Neural-Network-Based Convex Regularizer for Inverse Problemscited by 40
- 2017Convolutional Dictionary Learning: A Comparative Review and New Algorithmscited by 23
- 2022PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularizationcited by 22
- 2023TorchDEQ: A Library for Deep Equilibrium Modelscited by 21
8 more
- 2017Convolutional Dictionary Learning via Local Processingcited by 19
- 2021Stable and Interpretable Unrolled Dictionary Learningcited by 15
- 2021A Generative Variational Model for Inverse Problems in Imagingcited by 14
- 2020Learning Multiscale Convolutional Dictionaries for Image Reconstructioncited by 11
- 2021Understanding approximate and unrolled dictionary learning for pattern recoverycited by 11
- 2017Convolutional Dictionary Learning: Acceleration and Convergencecited by 6
- 2021DCT2net: an interpretable shallow CNN for image denoisingcited by 6
- 2014A fast patch-dictionary method for whole image recoverycited by 5
Built on by
Citing papers per year: 2025: 3.
3 papers.