Denoising Prior Driven Deep Neural Network for Image Restoration

Abstract

Deep neural networks (DNNs) have shown very promising results for various image restoration (IR) tasks. However, the design of network architectures remains a major challenging for achieving further improvements. While most existing DNN-based methods solve the IR problems by directly mapping low quality images to desirable high-quality images, the observation models characterizing the image degradation processes have been largely ignored. In this paper, we first propose a denoising-based IR algorithm, whose iterative steps can be computed efficiently. Then, the iterative process is unfolded into a deep neural network, which is composed of multiple denoisers modules interleaved with back-projection (BP) modules that ensure the observation consistencies. A convolutional neural network (CNN) based denoiser that can exploit the multi-scale redundancies of natural images is proposed. As such, the proposed network not only exploits the powerful denoising ability of DNNs, but also leverages the prior of the observation model. Through end-to-end training, both the denoisers and the BP modules can be jointly optimized. Experimental results on several IR tasks, e.g., image denoisig, super-resolution and deblurring show that the proposed method can lead to very competitive and often state-of-the-art results on several IR tasks, including image denoising, deblurring and super-resolution.

14page, 11 figures

References in corpus (4)

• Fully Convolutional Networks for Semantic Segmentation
• Deep Learning for Generic Object Detection: A Survey
• First-order Methods Almost Always Avoid Saddle Points
• Image Restoration using Autoencoding Priors

Cited by in corpus (60)

• AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing
• COAST: COntrollable Arbitrary-Sampling NeTwork for Compressive Sensing
• RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
• Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing
• Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network
• Content-aware Scalable Deep Compressed Sensing
• Memory-Augmented Deep Unfolding Network for Compressive Sensing
• Image Compressed Sensing Using Non-local Neural Network
• Learning to Optimize: A Primer and A Benchmark
• A Two-Stage Attentive Network for Single Image Super-Resolution
• Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• Residual Dense Network for Image Restoration
• Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network
• Provable Convergence of Plug-and-Play Priors with MMSE denoisers
• Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal
• Fixed-Point and Objective Convergence of Plug-and-Play Algorithms
• Unified Single-Image and Video Super-Resolution via Denoising Algorithms
• Plug-and-play ISTA converges with kernel denoisers
• Biomedical Image Reconstruction: From the Foundations to Deep Neural Networks
• On Plug-and-Play Regularization using Linear Denoisers
• Bayesian Image Super-Resolution with Deep Modeling of Image Statistics
• End-to-end joint optimization of metasurface and image processing for compact snapshot hyperspectral imaging
• Deep Unfolding with Normalizing Flow Priors for Inverse Problems
• Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
• Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction
• Sketch-Guided Scenery Image Outpainting
• Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
• A New Recurrent Plug-and-Play Prior Based on the Multiple Self-Similarity Network
• Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis
• Integrating neural networks into the blind deblurring framework to compete with the end-to-end learning-based methods
• Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing
• On the Proof of Fixed-Point Convergence for Plug-and-Play ADMM
• Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
• Provable Preconditioned Plug-and-Play Approach for Compressed Sensing MRI Reconstruction
• Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
• Plug-and-Play Regularization using Linear Solvers
• Rank-One Network: An Effective Framework for Image Restoration
• On the Contractivity of Plug-and-Play Operators
• ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensing
• Convex Regularization Behind Neural Reconstruction
• Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition
• DIVA: Deep Unfolded Network from Quantum Interactive Patches for Image Restoration
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
• Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
• Scalable Plug-and-Play ADMM with Convergence Guarantees
• Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
• Deep Low-rank plus Sparse Network for Dynamic MR Imaging
• Evolutionary Variational Optimization of Generative Models
• Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution
• MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction
• Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision
• Scalable Deep Compressive Sensing
• Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolution
• Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration
• Deep Spatial-angular Regularization for Compressive Light Field Reconstruction over Coded Apertures
• Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement
• Investigating Customization Strategies and Convergence Behaviors of Task-specific ADMM
• A novel extension of Generalized Low-Rank Approximation of Matrices based on multiple-pairs of transformations
• Searching Efficient Model-guided Deep Network for Image Denoising