Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problems
Not on the map. Why?
Abstract (arXiv)
Unrolled networks have become prevalent in various computer vision and imaging tasks. Although they have demonstrated remarkable efficacy in solving specific computer vision and computational imaging tasks, their adaptation to other applications presents considerable challenges. This is primarily due to the multitude of design decisions that practitioners working on new applications must navigate, each potentially affecting the network's overall performance. These decisions include selecting the optimization algorithm, defining the loss function, and determining the number of convolutional layers, among others. Compounding the issue, evaluating each design choice requires time-consuming simulations to train, fine-tune the neural network, and optimize for its performance. As a result, the process of exploring multiple options and identifying the optimal configuration becomes time-consuming and computationally demanding. The main objectives of this paper are (1) to unify some ideas and methodologies used in unrolled networks to reduce the number of design choices a user has to make, and (2) to report a comprehensive ablation study to discuss the impact of each of the choices involved in designing unrolled networks and present practical recommendations based on our findings. We anticipate that this study will help scientists and engineers design unrolled networks for their applications and diagnose problems within their networks efficiently.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 36 of its 63 references that are in the map. First posted on arXiv 8 Jan 2025.
Builds on
36 of 63 references.
References · 36
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2016Identity Mappings in Deep Residual Networkscited by 1,965
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
- 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
- 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
- 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 307
- 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 291
- 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
- 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 132
- 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 127
- 2022Deep Generalized Unfolding Networks for Image Restorationcited by 121
24 more
- 2022Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imagingcited by 96
- 2017A Review of Convolutional Neural Networks for Inverse Problems in Imagingcited by 81
- 2023Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusioncited by 78
- 2014From Denoising to Compressed Sensingcited by 68
- 2020AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensingcited by 68
- 2017One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Modelscited by 67
- 2017Learned D-AMP: Principled Neural Network based Compressive Image Recoverycited by 65
- 2018Compressed Sensing with Deep Image Prior and Learned Regularizationcited by 47
- 2018Neural Proximal Gradient Descent for Compressive Imagingcited by 46
- 2017Unrolled Optimization with Deep Priorscited by 40
- 2017Learning to Invert: Signal Recovery via Deep Convolutional Networkscited by 22
- 2020Model Adaptation for Inverse Problems in Imagingcited by 21
- 2024Stochastic Deep Restoration Priors for Imaging Inverse Problemscited by 14
- 2020Do CNNs solve the CT inverse problem?cited by 13
- 2019Neumann Networks for Inverse Problems in Imagingcited by 9
- 2023PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstructioncited by 9
- 2017DeepCodec: Adaptive Sensing and Recovery via Deep Convolutional Neural Networkscited by 8
- 2023Block Coordinate Plug-and-Play Methods for Blind Inverse Problemscited by 8
- 2023Self-Supervised Scalable Deep Compressed Sensingcited by 8
- 2020Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scanscited by 7
- 2021Deep Algorithm Unrolling for Biomedical Imagingcited by 6
- 2024Practical Compact Deep Compressed Sensingcited by 4
- 2023MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Datacited by 3
- 2022Denoising Generalized Expectation-Consistent Approximation for MR Image Recoverycited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.