Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Abstract

Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise (AWGN) at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks such as Gaussian denoising, single image super-resolution and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• ADADELTA: An Adaptive Learning Rate Method
• On learning optimized reaction diffusion processes for effective image restoration
• Analyzing the group sparsity based on the rank minimization methods

Cited by in corpus (905)

• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• MoDL: Model Based Deep Learning Architecture for Inverse Problems
• Robust Real-World Image Super-Resolution against Adversarial Attacks
• Deep Bilateral Learning for Real-Time Image Enhancement
• Artificial Intelligence in the Creative Industries: A Review
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Machine learning in acoustics: theory and applications
• Denoising Prior Driven Deep Neural Network for Image Restoration
• Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network
• Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network
• Rank Minimization for Snapshot Compressive Imaging
• R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
• Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
• SAR Image Despeckling Using a Convolutional Neural Network
• Target-adaptive CNN-based pansharpening
• An Iterative BP-CNN Architecture for Channel Decoding
• Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning
• LocalViT: Analyzing Locality in Vision Transformers
• Loss Functions and Metrics in Deep Learning
• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video
• Non-Local Recurrent Network for Image Restoration
• Deep learning approach to Fourier ptychographic microscopy
• Plug and play methods for magnetic resonance imaging (long version)
• Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
• Deep Residual Learning for Channel Estimation in Intelligent Reflecting Surface-Assisted Multi-User Communications
• On the use of deep learning for phase recovery
• Temporal Context Mining for Learned Video Compression
• Comparison of Image Quality Models for Optimization of Image Processing Systems
• Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
• Multi-Frame Quality Enhancement for Compressed Video
• SUNet: Swin Transformer UNet for Image Denoising
• EnlightenGAN: Deep Light Enhancement without Paired Supervision
• Restormer: Efficient Transformer for High-Resolution Image Restoration
• MemNet: A Persistent Memory Network for Image Restoration
• Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image
• Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
• Event-Based Fusion for Motion Deblurring with Cross-modal Attention
• Enhanced CNN for image denoising
• Deep Graph-Convolutional Image Denoising
• Real-world Noisy Image Denoising: A New Benchmark
• Deep Residual Learning for Compressed Sensing CT Reconstruction via Persistent Homology Analysis
• Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera
• Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network
• SAR2SAR: a semi-supervised despeckling algorithm for SAR images
• Image Restoration for Remote Sensing: Overview and Toolbox
• Deep Learning-Based Video Coding: A Review and A Case Study
• RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
• Probabilistic Noise2Void: Unsupervised Content-Aware Denoising
• Learned Image Downscaling for Upscaling using Content Adaptive Resampler
• Moiré Photo Restoration Using Multiresolution Convolutional Neural Networks
• Multi-Channel Deep Networks for Block-Based Image Compressive Sensing
• WINNet: Wavelet-inspired Invertible Network for Image Denoising
• Noise2Inverse: Self-supervised deep convolutional denoising for tomography
• Deformable Kernel Networks for Joint Image Filtering
• Deep Identity-aware Transfer of Facial Attributes
• Method for motion artifact reduction using a convolutional neural network for dynamic contrast enhanced MRI of the liver
• High-throughput molecular imaging via deep learning enabled Raman spectroscopy
• Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
• DVDnet: A Fast Network for Deep Video Denoising
• Learning Deep CNN Denoiser Prior for Image Restoration
• DeepSUM: Deep neural network for Super-resolution of Unregistered Multitemporal images
• Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising
• Pre-Trained Image Processing Transformer
• Can learning from natural image denoising be used for seismic data interpolation?
• Deep Learning-Aided 6G Wireless Networks: A Comprehensive Survey of Revolutionary PHY Architectures
• Content-aware Scalable Deep Compressed Sensing
• Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network
• Path-Restore: Learning Network Path Selection for Image Restoration
• Memory-Augmented Deep Unfolding Network for Compressive Sensing
• Autonomous Extraction of Millimeter-scale Deformation in InSAR Time Series Using Deep Learning
• Deep Plug-and-play Prior for Low-rank Tensor Completion
• Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction
• Uformer: A General U-Shaped Transformer for Image Restoration
• Residual-driven Fuzzy C-Means Clustering for Image Segmentation
• Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
• Watch Me, but Don't Touch Me! Contactless Control Flow Monitoring via Electromagnetic Emanations
• Review: Deep Learning in Electron Microscopy
• Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
• Image Compressed Sensing Using Non-local Neural Network
• InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
• deSpeckNet: Generalizing Deep Learning Based SAR Image Despeckling
• PaDNet: Pan-Density Crowd Counting
• COLA-Net: Collaborative Attention Network for Image Restoration
• Large-scale phase retrieval
• A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
• NLH: A Blind Pixel-level Non-local Method for Real-world Image Denoising
• Self-supervised Image Enhancement Network: Training with Low Light Images Only
• ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
• A Benchmark for Edge-Preserving Image Smoothing
• A Deep Journey into Super-resolution: A survey
• Deepfake Detection: A Comprehensive Survey from the Reliability Perspective
• Noise2Fast: Fast Self-Supervised Single Image Blind Denoising
• Kindling the Darkness: A Practical Low-light Image Enhancer
• Spatial-Spectral Fusion by Combining Deep Learning and Variation Model
• A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• SwinIR: Image Restoration Using Swin Transformer
• Federated Learning on Non-IID Data Silos: An Experimental Study
• Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer
• SAR Image Despeckling by Deep Neural Networks: from a pre-trained model to an end-to-end training strategy
• Efficient and Effective Context-Based Convolutional Entropy Modeling for Image Compression
• Learning Converged Propagations with Deep Prior Ensemble for Image Enhancement
• Deep Learning for Joint Channel Estimation and Feedback in Massive MIMO Systems
• Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network
• Class-Aware Fully-Convolutional Gaussian and Poisson Denoising
• GAP-net for Snapshot Compressive Imaging
• Pyramid Attention Networks for Image Restoration
• Deep Plug-and-Play Prior for Hyperspectral Image Restoration
• Computationally Efficient Deep Neural Network for Computed Tomography Image Reconstruction
• Performance characterization of a novel deep learning-based MR image reconstruction pipeline
• Variational Deep Image Restoration
• Efficient Multi-Stage Video Denoising with Recurrent Spatio-Temporal Fusion
• Deep Mean-Shift Priors for Image Restoration
• Learning Enriched Features for Real Image Restoration and Enhancement
• Learning to Adapt to Light
• Bridging the Gap Between Computational Photography and Visual Recognition
• Visual Attention Network for Low Dose CT
• Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration
• Toward Convolutional Blind Denoising of Real Photographs
• A Universal Deep Learning Framework for Real-Time Denoising of Ultrasound Images
• Deep Spectral CNN for Laser Induced Breakdown Spectroscopy
• Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement
• GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks
• All-optical image denoising using a diffractive visual processor
• Residual Dense Network for Image Restoration
• Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
• Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
• Light Field Denoising via Anisotropic Parallax Analysis in a CNN Framework
• Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network
• A Cascaded Convolutional Neural Network for X-ray Low-dose CT Image Denoising
• Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression
• One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
• Provable Convergence of Plug-and-Play Priors with MMSE denoisers
• Multi-scale Convolutional Neural Networks for Inverse Problems
• SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priors
• Unsupervised Learning with Stein's Unbiased Risk Estimator
• SuperDTI: Ultrafast diffusion tensor imaging and fiber tractography with deep learning
• Multi-Stage Progressive Image Restoration
• NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Results
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise
• Deep Iterative Reconstruction for Phase Retrieval
• Square Kilometre Array Science Data Challenge 1: analysis and results
• Convolutional Proximal Neural Networks and Plug-and-Play Algorithms
• Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal
• Progressive Joint Low-light Enhancement and Noise Removal for Raw Images
• A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends
• TBC-Net: A real-time detector for infrared small target detection using semantic constraint
• Non-Convex Weighted Lp Minimization based Group Sparse Representation Framework for Image Denoising
• Fixed-Point and Objective Convergence of Plug-and-Play Algorithms
• Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images
• RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding
• Color Image and Multispectral Image Denoising Using Block Diagonal Representation
• xQSM: Quantitative Susceptibility Mapping with Octave Convolutional and Noise Regularized Neural Networks
• Image reconstruction algorithms in radio interferometry: from handcrafted to learned regularization denoisers
• Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
• MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
• Attribute Artifacts Removal for Geometry-based Point Cloud Compression
• Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
• Deep Interference Mitigation and Denoising of Real-World FMCW Radar Signals
• Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis
• Unified Single-Image and Video Super-Resolution via Denoising Algorithms
• Three-dimensional Optical Coherence Tomography Image Denoising through Multi-input Fully-Convolutional Networks
• Deep learning-based statistical noise reduction for multidimensional spectral data
• Quality-Gated Convolutional LSTM for Enhancing Compressed Video
• Time-Travel Rephotography
• Plug-and-play ISTA converges with kernel denoisers
• Correction by Projection: Denoising Images with Generative Adversarial Networks
• Learning to See in the Dark
• Fingerprint Presentation Attack Detection by Channel-wise Feature Denoising
• Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
• Deep Idempotent Network for Efficient Single Image Blind Deblurring
• Model-Based Image Signal Processors via Learnable Dictionaries
• Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
• Fast High-Dimensional Bilateral and Nonlocal Means Filtering
• Quaternion Nuclear Norm minus Frobenius Norm Minimization for color image reconstruction
• High-throughput Onboard Hyperspectral Image Compression with Ground-based CNN Reconstruction
• Solar image denoising with convolutional neural networks
• Texture variation adaptive image denoising with nonlocal PCA
• Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising
• Natural Image Noise Dataset
• On Plug-and-Play Regularization using Linear Denoisers
• Learning Deformable Kernels for Image and Video Denoising
• MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising
• Denoised Smoothing: A Provable Defense for Pretrained Classifiers
• DCT2net: an interpretable shallow CNN for image denoising
• Optimal Transport for Unsupervised Denoising Learning
• Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless Systems
• Depth Estimation and Image Restoration by Deep Learning from Defocused Images
• Snapshot Ptychography on Array cameras
• Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction
• Multi-level Wavelet-CNN for Image Restoration
• First AI for deep super-resolution wide-field imaging in radio astronomy: unveiling structure in ESO 137--006
• Toward Robust Autotuning of Noisy Quantum Dot Devices
• Massive MIMO Channel Prediction Via Meta-Learning and Deep Denoising: Is a Small Dataset Enough?
• PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds
• DeepRED: Deep Image Prior Powered by RED
• Connections between Deep Equilibrium and Sparse Representation Models with Application to Hyperspectral Image Denoising
• Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization
• LIDIA: Lightweight Learned Image Denoising with Instance Adaptation
• Bayesian Image Super-Resolution with Deep Modeling of Image Statistics
• Deep Learning based Switching Filter for Impulsive Noise Removal in Color Images
• A Novel Image Denoising Algorithm Using Concepts of Quantum Many-Body Theory
• Robust and interpretable blind image denoising via bias-free convolutional neural networks
• Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
• The Practicality of Stochastic Optimization in Imaging Inverse Problems
• SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
• CDLNet: Noise-Adaptive Convolutional Dictionary Learning Network for Blind Denoising and Demosaicing
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling
• Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT
• Towards CT-quality Ultrasound Imaging using Deep Learning
• High Perceptual Quality Image Denoising with a Posterior Sampling CGAN
• Benchmarking Deep Learning-Based Low-Dose CT Image Denoising Algorithms
• Night Time Haze and Glow Removal using Deep Dilated Convolutional Network
• CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising
• ReconResNet: Regularised Residual Learning for MR Image Reconstruction of Undersampled Cartesian and Radial Data
• Multi-modal Deep Guided Filtering for Comprehensible Medical Image Processing
• Unsupervised Deep Contrast Enhancement with Power Constraint for OLED Displays
• Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
• A deep convolutional neural network for salt-and-pepper noise removal using selective convolutional blocks
• Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric
• VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications
• Bilateral Spectrum Weighted Total Variation for Noisy-Image Super-Resolution and Image Denoising
• Investigating Task-driven Latent Feasibility for Nonconvex Image Modeling
• Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
• JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
• Burst Denoising with Kernel Prediction Networks
• Fast, nonlocal and neural: a lightweight high quality solution to image denoising
• Non-Local Video Denoising by CNN
• Neural Nearest Neighbors Networks
• Deep Residual Autoencoder for quality independent JPEG restoration
• A new approach for the statistical denoising of Planck interstellar dust polarization data
• An Unsupervised Reconstruction Method For Low-Dose CT Using Deep Generative Regularization Prior
• HINet: Half Instance Normalization Network for Image Restoration
• Selective Residual M-Net for Real Image Denoising
• Very Lightweight Photo Retouching Network with Conditional Sequential Modulation
• Deep Learning on Image Denoising: An overview
• Plug-and-Play Quantum Adaptive Denoiser for Deconvolving Poisson Noisy Images
• Deep Learning Techniques for Geospatial Data Analysis
• Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation
• Remote Heart Rate Measurement from Highly Compressed Facial Videos: an End-to-end Deep Learning Solution with Video Enhancement
• Towards Real-World Blind Face Restoration with Generative Facial Prior
• Block-Matching Convolutional Neural Network for Image Denoising
• SiSPRNet: End-to-End Learning for Single-Shot Phase Retrieval
• When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
• MGANet: A Robust Model for Quality Enhancement of Compressed Video
• DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering
• RCRN: Real-world Character Image Restoration Network via Skeleton Extraction
• Weak-signal extraction enabled by deep-neural-network denoising of diffraction data
• Recovering Loss to Followup Information Using Denoising Autoencoders
• Multi-Resolution Data Fusion for Super Resolution Imaging
• Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations
• BlockCNN: A Deep Network for Artifact Removal and Image Compression
• A multiscale neural network based on hierarchical matrices
• Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation
• Unsupervised Degradation Representation Learning for Blind Super-Resolution
• Adaptive Block Compressive Sensing: towards a real-time and low-complexity implementation
• Real-time Streaming Video Denoising with Bidirectional Buffers
• CycleISP: Real Image Restoration via Improved Data Synthesis
• Burst Photography for Learning to Enhance Extremely Dark Images
• PNEN: Pyramid Non-Local Enhanced Networks
• Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
• Deep learning-based denoising for fast time-resolved flame emission spectroscopy in high-pressure combustion environment
• Spatiotemporal singular value decomposition for denoising in photoacoustic imaging with low-energy excitation light source
• Ghost Imaging Based on Recurrent Neural Network
• Deep neural networks-based denoising models for CT imaging and their efficacy
• Deep Learning-based Channel Estimation for Beamspace mmWave Massive MIMO Systems
• Wide Inference Network for Image Denoising via Learning Pixel-distribution Prior
• Training Deep Learning Based Denoisers without Ground Truth Data
• DnSwin: Toward Real-World Denoising via Continuous Wavelet Sliding-Transformer
• Image inpainting using frequency domain priors
• Attention Cube Network for Image Restoration
• Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks
• On The Classification-Distortion-Perception Tradeoff
• Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution
• CTU Depth Decision Algorithms for HEVC: A Survey
• Free-Electron Ramsey-Type Interferometry for Enhanced Amplitude and Phase imaging of Nearfields
• CameraNet: A Two-Stage Framework for Effective Camera ISP Learning
• Real-World Remote Sensing Image Dehazing: Benchmark and Baseline
• Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition
• MRI denoising using Deep Learning and Non-local averaging
• Connecting Image Denoising and High-Level Vision Tasks via Deep Learning
• Multi-wavelet residual dense convolutional neural network for image denoising
• Algorithm-driven Advances for Scientific CT Instruments: From Model-based to Deep Learning-based Approaches
• Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
• Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization
• Automatic image-domain Moire artifact reduction method in grating-based x-ray interferometry imaging
• Residual Knowledge Distillation
• FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table
• Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
• Combining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering
• Gradient Step Denoiser for convergent Plug-and-Play
• Wasserstein Patch Prior for Image Superresolution
• DIR-DBTnet: Deep iterative reconstruction network for 3D digital breast tomosynthesis imaging
• Deep artifact learning for compressed sensing and parallel MRI
• NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images
• prDeep: Robust Phase Retrieval with a Flexible Deep Network
• A New Recurrent Plug-and-Play Prior Based on the Multiple Self-Similarity Network
• Securing Fixed Neural Network Steganography
• Improving Synthetically Generated Image Detection in Cross-Concept Settings
• Self-supervised Low Light Image Enhancement and Denoising
• Efficient Blind-Spot Neural Network Architecture for Image Denoising
• CoIL: Coordinate-based Internal Learning for Imaging Inverse Problems
• Atmospheric turbulence removal using convolutional neural network
• Joint Multi-Scale Tone Mapping and Denoising for HDR Image Enhancement
• Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression
• Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables
• Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces
• NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
• k-Space Deep Learning for Accelerated MRI
• On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent
• When AWGN-based Denoiser Meets Real Noises
• Zero-shot super-resolution with a physically-motivated downsampling kernel for endomicroscopy
• A Practical Solution for SAR Despeckling With Adversarial Learning Generated Speckled-to-Speckled Images
• Marine Snow Removal Benchmarking Dataset
• Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration
• Riesz-Quincunx-UNet Variational Auto-Encoder for Satellite Image Denoising
• Low-Light Hyperspectral Image Enhancement
• Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising
• Momentum-Net: Fast and convergent iterative neural network for inverse problems
• UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space
• Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack
• W-Net: Two-stage U-Net with misaligned data for raw-to-RGB mapping
• Progressive Image Deraining Networks: A Better and Simpler Baseline
• Image Denoising using Attention-Residual Convolutional Neural Networks
• Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
• Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging
• Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
• Joint Demosaicking and Denoising Benefits from a Two-stage Training Strategy
• Clinical Micro-CT Empowered by Interior Tomography, Robotic Scanning, and Deep Learning
• Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
• Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data
• A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising
• Electro-Magnetic Side-Channel Attack Through Learned Denoising and Classification
• AccessFixer: Enhancing GUI Accessibility for Low Vision Users With R-GCN Model
• Segmentation-Aware Image Denoising without Knowing True Segmentation
• Two-stage Deep Denoising with Self-guided Noise Attention for Multimodal Medical Images
• Data Dropout: Optimizing Training Data for Convolutional Neural Networks
• A Poisson-Gaussian Denoising Dataset with Real Fluorescence Microscopy Images
• Poisoned classifiers are not only backdoored, they are fundamentally broken
• Fast Single Image Rain Removal via a Deep Decomposition-Composition Network
• Deep Learning for Predictive Analytics in Reversible Steganography
• Distributed Learning and Inference with Compressed Images
• An Experimental-based Review of Image Enhancement and Image Restoration Methods for Underwater Imaging
• A Novel Convolutional Neural Network for Image Steganalysis with Shared Normalization
• Physics-based Noise Modeling for Extreme Low-light Photography
• Denoising of Three-Dimensional Fast Spin Echo Magnetic Resonance Images of Knee Joints using Spatial-Variant Noise-Relevant Residual Learning of Convolution Neural Network
• Provable Preconditioned Plug-and-Play Approach for Compressed Sensing MRI Reconstruction
• Dual Adversarial Network: Toward Real-world Noise Removal and Noise Generation
• Chaining Identity Mapping Modules for Image Denoising
• Video Denoising and Enhancement via Dynamic Video Layering
• Training Robust Deep Neural Networks via Adversarial Noise Propagation
• Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
• Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser
• Blind Face Restoration via Deep Multi-scale Component Dictionaries
• Sampling methods for efficient training of graph convolutional networks: A survey
• Interpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding
• Autofocusing+: Noise-Resilient Motion Correction in Magnetic Resonance Imaging
• Toward ground-truth optical coherence tomography via three-dimensional unsupervised deep learning processing and data
• Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
• Denoising of 3D MR images using a voxel-wise hybrid residual MLP-CNN model to improve small lesion diagnostic confidence
• GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling
• Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations
• Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusion
• Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
• Learned, uncertainty-driven adaptive acquisition for photon-efficient scanning microscopy
• Data-driven geophysics: from dictionary learning to deep learning
• Nest-DGIL: Nesterov-optimized Deep Geometric Incremental Learning for CS Image Reconstruction
• Image Deconvolution via Noise-Tolerant Self-Supervised Inversion
• Total Deep Variation: A Stable Regularizer for Inverse Problems
• DHP: Differentiable Meta Pruning via HyperNetworks
• Unsupervised Image Noise Modeling with Self-Consistent GAN
• Multi-band Weighted $l_p$ Norm Minimization for Image Denoising
• Classification and reconstruction of optical quantum states with deep neural networks
• Plug-and-Play Regularization using Linear Solvers
• A Multi-Head Convolutional Neural Network With Multi-path Attention improves Image Denoising
• LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN
• SSP-IR: Semantic and Structure Priors for Diffusion-based Realistic Image Restoration
• GIA-Net: Global Information Aware Network for Low-light Imaging
• Probabilistic-based Feature Embedding of 4-D Light Fields for Compressive Imaging and Denoising
• Depth image denoising using nuclear norm and learning graph model
• Noise2Void - Learning Denoising from Single Noisy Images
• Contextual colorization and denoising for low-light ultra high resolution sequences
• Low-Dose CT Image Denoising Using Parallel-Clone Networks
• Invertible Denoising Network: A Light Solution for Real Noise Removal
• Learning a Dilated Residual Network for SAR Image Despeckling
• Image Restoration for Under-Display Camera
• Convolutional Neural Network based Multiple-Rate Compressive Sensing for Massive MIMO CSI Feedback: Design, Simulation, and Analysis
• A Comparative Study of Deep Learning and Iterative Algorithms for Joint Channel Estimation and Signal Detection in OFDM Systems
• Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images
• Fast and Robust Cascade Model for Multiple Degradation Single Image Super-Resolution
• Rank-One Network: An Effective Framework for Image Restoration
• A Lite Distributed Semantic Communication System for Internet of Things
• DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal
• TMP: Temporal Motion Propagation for Online Video Super-Resolution
• PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors
• Regularizing linear inverse problems with convolutional neural networks
• RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining
• ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer
• Adaptive Denoising via GainTuning
• Efficient Physics-Based Learned Reconstruction Methods for Real-Time 3D Near-Field MIMO Radar Imaging
• Astronomical image denoising by self-supervised deep learning and restoration processes
• Nonlinear Power Method for Computing Eigenvectors of Proximal Operators and Neural Networks
• X-GANs: Image Reconstruction Made Easy for Extreme Cases
• GroupCDL: Interpretable Denoising and Compressed Sensing MRI via Learned Group-Sparsity and Circulant Attention
• Neural Network Methods for Radiation Detectors and Imaging
• First image then video: A two-stage network for spatiotemporal video denoising
• Semantic Image Completion and Enhancement using Deep Learning
• Designing Stable Neural Networks using Convex Analysis and ODEs
• Zero-Shot Image Denoising for High-Resolution Electron Microscopy
• Designing and Training of A Dual CNN for Image Denoising
• Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography
• Deep Learning for Image Denoising: A Survey
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• Which Contrast Does Matter? Towards a Deep Understanding of MR Contrast using Collaborative GAN
• Supervised Learning of Sparsity-Promoting Regularizers for Denoising
• Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
• Neural Sparse Representation for Image Restoration
• Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising
• Multi-scale Processing of Noisy Images using Edge Preservation Losses
• Deep Learning Techniques for Inverse Problems in Imaging
• Deep Neural Network-Based Quantized Signal Reconstruction for DOA Estimation
• Efficient and Generic 1D Dilated Convolution Layer for Deep Learning
• Seismic data denoising and deblending using deep learning
• NormalNet: Learning-based Normal Filtering for Mesh Denoising
• Learning from Natural Noise to Denoise Micro-Doppler Spectrogram
• B-DRRN: A Block Information Constrained Deep Recursive Residual Network for Video Compression Artifacts Reduction
• Group Sparsity Residual Constraint for Image Denoising
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images
• Visualized Insights into the Optimization Landscape of Fully Convolutional Networks
• Unsupervised Modality-Transferable Video Highlight Detection with Representation Activation Sequence Learning
• Regularization by Denoising Sub-sampled Newton Method for Spectral CT Multi-Material Decomposition
• Amplitude SAR Imagery Splicing Localization
• Unsupervised Single Image Deraining with Self-supervised Constraints
• Polynomial Neural Fields for Subband Decomposition and Manipulation
• FastPET: Near Real-Time PET Reconstruction from Histo-Images Using a Neural Network
• Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization
• Non-Local Part-Aware Point Cloud Denoising
• Learning Invariant Representation for Unsupervised Image Restoration
• Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration
• External Patch-Based Image Restoration Using Importance Sampling
• On the Contractivity of Plug-and-Play Operators
• Simultaneous Fidelity and Regularization Learning for Image Restoration
• Linear Combinations of Patches are Unreasonably Effective for Single-Image Denoising
• Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN
• Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability
• Performance versus Complexity Study of Neural Network Equalizers in Coherent Optical Systems
• Self-Supervised Fast Adaptation for Denoising via Meta-Learning
• A deep network for sinogram and CT image reconstruction
• Supervision by Denoising for Medical Image Segmentation
• Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
• SIP-SegNet: A Deep Convolutional Encoder-Decoder Network for Joint Semantic Segmentation and Extraction of Sclera, Iris and Pupil based on Periocular Region Suppression
• Unsupervised Denoising for Satellite Imagery using Wavelet Subband CycleGAN
• End-to-End Denoising of Dark Burst Images Using Recurrent Fully Convolutional Networks
• Unrolled Wirtinger Flow with Deep Decoding Priors for Phaseless Imaging
• Iterative Low-rank Network for Hyperspectral Image Denoising
• Exploring Gradient Flow Based Saliency for DNN Model Compression
• A General Decoupled Learning Framework for Parameterized Image Operators
• DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation
• Representing Noisy Image Without Denoising
• Perceptually Optimized Generative Adversarial Network for Single Image Dehazing
• Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution
• Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
• Learning to Sample the Most Useful Training Patches from Images
• An ELU Network with Total Variation for Image Denoising
• Basis Prediction Networks for Effective Burst Denoising with Large Kernels
• Multi-bin Trainable Linear Unit for Fast Image Restoration Networks
• DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images
• OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers
• Non-Local ConvLSTM for Video Compression Artifact Reduction
• Real-Time Text Detection and Recognition
• Learning Filter Basis for Convolutional Neural Network Compression
• LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CT
• Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach
• Generating High Quality Visible Images from SAR Images Using CNNs
• Noise-robust latent vector reconstruction in ptychography using deep generative models
• Plug-and-Play Algorithms for Video Snapshot Compressive Imaging
• Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis
• CNN-Based Real-Time Parameter Tuning for Optimizing Denoising Filter Performance
• Weighted Sigmoid Gate Unit for an Activation Function of Deep Neural Network
• A Set-Theoretic Study of the Relationships of Image Models and Priors for Restoration Problems
• Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement
• Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations
• Unrolled Compressed Blind-Deconvolution
• Conditional Variational Autoencoder for Learned Image Reconstruction
• Neural Blind Deconvolution Using Deep Priors
• 2.5D Deep Learning for CT Image Reconstruction using a Multi-GPU implementation
• Deep learning-based deconvolution for interferometric radio transient reconstruction
• SNIPS: Solving Noisy Inverse Problems Stochastically
• Deep Stacked Networks with Residual Polishing for Image Inpainting
• Operational vs Convolutional Neural Networks for Image Denoising
• AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising
• Learning Asymmetric and Local Features in Multi-Dimensional Data through Wavelets with Recursive Partitioning
• Low-light Image Restoration with Short- and Long-exposure Raw Pairs
• Multi-frame Joint Enhancement for Early Interlaced Videos
• BAM: A Balanced Attention Mechanism for Single Image Super Resolution
• Unsupervised MR Motion Artifact Deep Learning using Outlier-Rejecting Bootstrap Aggregation
• Deep residual learning in CT physics: scatter correction for spectral CT
• Self-supervised Hyperspectral Image Restoration using Separable Image Prior
• Noise2Astro: Astronomical Image Denoising With Self-Supervised NeuralNetworks
• Spatial-Adaptive Network for Single Image Denoising
• HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization
• Joint self-supervised blind denoising and noise estimation
• Structured Output Learning with Conditional Generative Flows
• Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration
• Multiple Description Convolutional Neural Networks for Image Compression
• Convex Regularization Behind Neural Reconstruction
• Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
• Compressive Computed Tomography Reconstruction through Denoising Approximate Message Passing
• Denoising Arterial Spin Labeling Cerebral Blood Flow Images Using Deep Learning
• DR-Net: Transmission Steered Single Image Dehazing Network with Weakly Supervised Refinement
• Degrees of Freedom Analysis of Unrolled Neural Networks
• Learning Content-Weighted Deep Image Compression
• Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding
• Cooperative Semantic Segmentation and Image Restoration in Adverse Environmental Conditions
• A New Deep Learning Method for Image Deblurring in Optical Microscopic Systems
• Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors
• DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement
• Learning Context-Based Non-local Entropy Modeling for Image Compression
• DA-DRN: Degradation-Aware Deep Retinex Network for Low-Light Image Enhancement
• Targeted Gradient Descent: A Novel Method for Convolutional Neural Networks Fine-tuning and Online-learning
• FastHyMix: Fast and Parameter-free Hyperspectral Image Mixed Noise Removal
• Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition
• How to Best Combine Demosaicing and Denoising?
• Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring
• Enhancing Diffusion Model Stability for Image Restoration via Gradient Management
• NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset
• Joint tone mapping and denoising of thermal infrared images via multi-scale Retinex and multi-task learning
• Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
• Lightweight HI source finding for next generation radio surveys
• An ADMM-Newton-CNN Numerical Approach to a TV Model for Identifying Discontinuous Diffusion Coefficients in Elliptic Equations: Convex Case with Gradient Observations
• Video Quality Enhancement Using Deep Learning-Based Prediction Models for Quantized DCT Coefficients in MPEG I-frames
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• CFSNet: Toward a Controllable Feature Space for Image Restoration
• Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation
• Super-Resolution Perception for Industrial Sensor Data
• The Power of Complementary Regularizers: Image Recovery via Transform Learning and Low-Rank Modeling
• Engineering nonlinear activation functions for all-optical neural networks via quantum interference
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction
• A Nonoverlapping Domain Decomposition Method for Extreme Learning Machines: Elliptic Problems
• Enhancing super-resolution ultrasound localisation through multi-frame deconvolution exploiting spatiotemporal coherence
• Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation
• Deep Learning Assisted Denoising of Experimental Micrographs
• Scalable Plug-and-Play ADMM with Convergence Guarantees
• CIS-Net: A Novel CNN Model for Spatial Image Steganalysis via Cover Image Suppression
• Gaussian is All You Need: A Unified Framework for Solving Inverse Problems via Diffusion Posterior Sampling
• DeepExtractor: Time-domain reconstruction of signals and glitches in gravitational wave data with deep learning
• Wide spectrum denoising (WSD) for superresolution microscopy imaging using compressed sensing and a high-resolution camera
• Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework
• An efficient feature-preserving PDE algorithm for image denoising based on a spatial-fractional anisotropic diffusion equation
• Robust Video Content Alignment and Compensation for Clear Vision Through the Rain
• Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable
• Unpaired Image Denoising
• A simple blind-denoising filter inspired by electrically coupled photoreceptors in the retina
• Identifying Recurring Patterns with Deep Neural Networks for Natural Image Denoising
• NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
• Reinforcement Learning of Self Enhancing Camera Image and Signal Processing
• FINO: Flow-based Joint Image and Noise Model
• CNN aided Weighted Interpolation for Channel Estimation in Vehicular Communications
• Fully Convolutional Pixel Adaptive Image Denoiser
• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
• Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network
• Unsupervised Image Denoising with Frequency Domain Knowledge
• Fully Adaptive Bayesian Algorithm for Data Analysis, FABADA
• Learning a Single Tucker Decomposition Network for Lossy Image Compression with Multiple Bits-Per-Pixel Rates
• Generalized Deep Image to Image Regression
• Spectral Denoising for Microphone Classification
• Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
• A resnet-based universal method for speckle reduction in optical coherence tomography images
• Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents
• Deep Learning for Low-Dose CT Denoising
• Image Denoising and Super-Resolution using Residual Learning of Deep Convolutional Network
• A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems
• Structural Residual Learning for Single Image Rain Removal
• Denoising Particle Beam Micrographs with Plug-and-Play Methods
• Deep Network Interpolation for Continuous Imagery Effect Transition
• Diagnosing and Preventing Instabilities in Recurrent Video Processing
• Global Adaptive Filtering Layer for Computer Vision
• Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser
• HDR Denoising and Deblurring by Learning Spatio-temporal Distortion Models
• Deep Residual Network Empowered Channel Estimation for IRS-Assisted Multi-User Communication Systems
• DIVA: Deep Unfolded Network from Quantum Interactive Patches for Image Restoration
• Joint Reconstruction and Calibration using Regularization by Denoising
• Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Network
• Efficient B-mode Ultrasound Image Reconstruction from Sub-sampled RF Data using Deep Learning
• Artefact removal in ground truth and noise model deficient sub-cellular nanoscopy images using auto-encoder deep learning
• Handling noise in image deblurring via joint learning
• Learning to Denoise and Decode: A Novel Residual Neural Network Decoder for Polar Codes
• Universal Face Restoration With Memorized Modulation
• Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
• URIE: Universal Image Enhancement for Visual Recognition in the Wild
• Evolutionary Variational Optimization of Generative Models
• Learned Block-based Hybrid Image Compression
• Unsupervised Spatial-spectral Network Learning for Hyperspectral Compressive Snapshot Reconstruction
• Performance of a convolutional autoencoder designed to remove electronic noise from p-type point contact germanium detector signals
• Image and Texture Independent Deep Learning Noise Estimation using Multiple Frames
• BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
• Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
• Mixed Graph Signal Analysis of Joint Image Denoising / Interpolation
• Solving the inverse problem of microscopy deconvolution with a residual Beylkin-Coifman-Rokhlin neural network
• Content-decoupled Contrastive Learning-based Implicit Degradation Modeling for Blind Image Super-Resolution
• Joint multi-dimensional dynamic attention and transformer for general image restoration
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent
• Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
• Sparse Mixture-of-Experts for Non-Uniform Noise Reduction in MRI Images
• Image Demoireing with Learnable Bandpass Filters
• Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising
• Free-breathing Cardiovascular MRI Using a Plug-and-Play Method with Learned Denoiser
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• Federated CycleGAN for Privacy-Preserving Image-to-Image Translation
• Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imaging
• BLNet: A Fast Deep Learning Framework for Low-Light Image Enhancement with Noise Removal and Color Restoration
• NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network
• Facial age estimation by deep residual decision making
• Transform and Bitstream Domain Image Classification
• Task-Driven Deep Image Enhancement Network for Autonomous Driving in Bad Weather
• Object Detection based on OcSaFPN in Aerial Images with Noise
• Differentiable Visual Computing
• Inverse Halftoning Through Structure-Aware Deep Convolutional Neural Networks
• Deep Reformulated Laplacian Tone Mapping
• SRDTI: Deep learning-based super-resolution for diffusion tensor MRI
• CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learning
• Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification
• Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations
• Deep Learning based Denoise Network for CSI Feedback in FDD Massive MIMO Systems
• Bringing Old Photos Back to Life
• Deep Unfolding of a Proximal Interior Point Method for Image Restoration
• Deep Learning with Inaccurate Training Data for Image Restoration
• LSD${}_2$ -- Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs
• NTIRE 2020 Challenge on Image Demoireing: Methods and Results
• Analog-to-digital conversion revolutionized by deep learning
• Single Image Brightening via Multi-Scale Exposure Fusion with Hybrid Learning
• Non-blind Image Restoration Based on Convolutional Neural Network
• Wavelet-Based Dual-Branch Network for Image Demoireing
• Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network
• Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video
• From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image Restoration
• Unpaired Learning of Deep Image Denoising
• AWNet: Attentive Wavelet Network for Image ISP
• SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition
• Attenuating Random Noise in Seismic Data by a Deep Learning Approach
• Deep Griffin-Lim Iteration
• Multi-level Wavelet Convolutional Neural Networks
• End-to-End JPEG Decoding and Artifacts Suppression Using Heterogeneous Residual Convolutional Neural Network
• Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration
• Learning to Structure an Image with Few Colors
• Pivotal Auto-Encoder via Self-Normalizing ReLU
• Deep Reference Generation with Multi-Domain Hierarchical Constraints for Inter Prediction
• Noise2Blur: Online Noise Extraction and Denoising
• High quality ultrasonic multi-line transmission through deep learning
• Retrieving genuine nonlinear Raman responses in ultrafast spectroscopy via deep learning
• Lightweight image super-resolution with enhanced CNN
• Multi-Density Attention Network for Loop Filtering in Video Compression
• Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Network
• Detection and Correction of Cardiac MR Motion Artefacts during Reconstruction from K-space
• Spectrum Translation for Cross-Spectral Ocular Matching
• Adaptive Direction-Guided Structure Tensor Total Variation
• ISP4ML: Understanding the Role of Image Signal Processing in Efficient Deep Learning Vision Systems
• R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery
• Convolutional Neural Networks Analyzed via Inverse Problem Theory and Sparse Representations
• Regularization by Denoising: Clarifications and New Interpretations
• MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data
• Continuous Facial Motion Deblurring
• Deep Decomposition Learning for Inverse Imaging Problems
• Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
• Smoother Network Tuning and Interpolation for Continuous-level Image Processing
• Meta-Optimization of Deep CNN for Image Denoising Using LSTM
• Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution
• New Computational Techniques for a Faster Variation of BM3D Image Denoising
• MoViDNN: A Mobile Platform for Evaluating Video Quality Enhancement with Deep Neural Networks
• FL-MISR: Fast Large-Scale Multi-Image Super-Resolution for Computed Tomography Based on Multi-GPU Acceleration
• Synthesizing Visual Illusions Using Generative Adversarial Networks
• Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
• Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline
• Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical Study
• Plug-and-Play Priors as a Score-Based Method
• Cycle-Constrained Adversarial Denoising Convolutional Network for PET Image Denoising: Multi-Dimensional Validation on Large Datasets with Reader Study and Real Low-Dose Data
• An Optimal Reduction of TV-Denoising to Adaptive Online Learning
• Image Restoration Using Deep Regulated Convolutional Networks
• Controlled Learning of Pointwise Nonlinearities in Neural-Network-Like Architectures
• Noise2Inpaint: Learning Referenceless Denoising by Inpainting Unrolling
• Understanding Deep Architectures with Reasoning Layer
• Deeply Learned Spectral Total Variation Decomposition
• High-dimensional Assisted Generative Model for Color Image Restoration
• Rethinking Deep Image Prior for Denoising
• Restore from Restored: Single Image Denoising with Pseudo Clean Image
• Non-local Channel Aggregation Network for Single Image Rain Removal
• Channel Estimation for RIS-Assisted mmWave Systems via Diffusion Models
• BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping
• Progressive residual learning for single image dehazing
• Model-Driven Deep Learning Method for Jammer Suppression in Massive Connectivity Systems
• Video Segmentation Learning Using Cascade Residual Convolutional Neural Network
• Blind Image Restoration without Prior Knowledge
• Reconstructing the Noise Manifold for Image Denoising
• Blur, Noise, and Compression Robust Generative Adversarial Networks
• View Blind-spot as Inpainting: Self-Supervised Denoising with Mask Guided Residual Convolution
• Real-time Noise Source Estimation of a Camera System from an Image and Metadata
• Posterior Sampling for Image Restoration using Explicit Patch Priors
• A lightweight convolutional neural network for image denoising with fine details preservation capability
• Toward Interactive Modulation for Photo-Realistic Image Restoration
• Noise-Level Estimation from Single Color Image Using Correlations Between Textures in RGB Channels
• Microscopy Image Restoration using Deep Learning on W2S
• Dense xUnit Networks
• Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising
• Seeing in the dark with recurrent convolutional neural networks
• Boundary-Preserved Deep Denoising of the Stochastic Resonance Enhanced Multiphoton Images
• Seismic Shot Gather Noise Localization Using a Multi-Scale Feature-Fusion-Based Neural Network
• Joint reconstruction-segmentation on graphs
• Attention-based network for low-light image enhancement
• Structured and Localized Image Restoration
• H-OWAN: Multi-distorted Image Restoration with Tensor 1x1 Convolution
• Concatenated Attention Neural Network for Image Restoration
• A Multiscale Image Denoising Algorithm Based On Dilated Residual Convolution Network
• Localized Motion Artifact Reduction on Brain MRI Using Deep Learning with Effective Data Augmentation Techniques
• Learning degraded image classification with restoration data fidelity
• Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling
• Freqformer: Frequency-Domain Transformer for 3-D Reconstruction and Quantification of Human Retinal Vasculature
• A HVS-inspired Attention to Improve Loss Metrics for CNN-based Perception-Oriented Super-Resolution
• Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithms
• Exploiting Non-Local Priors via Self-Convolution For Highly-Efficient Image Restoration
• The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
• Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
• Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications
• A Review of an Old Dilemma: Demosaicking First, or Denoising First?
• DeepInit Phase Retrieval
• Rethinking deinterlacing for early interlaced videos
• Online Regularization by Denoising with Applications to Phase Retrieval
• ReTiDe: Real-Time Denoising for Energy-Efficient Motion Picture Processing with FPGAs
• An Effective Image Restorer: Denoising and Luminance Adjustment for Low-photon-count Imaging
• Superpixel-Guided Label Softening for Medical Image Segmentation
• A deep learning approach to detecting volcano deformation from satellite imagery using synthetic datasets
• Adaptive Regularization via Residual Smoothing in Deep Learning Optimization
• Performance Analysis of Plug-and-Play ADMM: A Graph Signal Processing Perspective
• Joint ptycho-tomography with deep generative priors
• T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing
• Flexible Image Denoising with Multi-layer Conditional Feature Modulation
• A Statistical Framework to Investigate the Optimality of Signal-Reconstruction Methods
• Controllable Confidence-Based Image Denoising
• DeepInSAR: A Deep Learning Framework for SAR Interferometric Phase Restoration and Coherence Estimation
• Highly Accelerated Multishot EPI through Synergistic Machine Learning and Joint Reconstruction
• NFCNN: Toward a Noise Fusion Convolutional Neural Network for Image Denoising
• Multi-temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation
• Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration
• Multi-Scale Deep Compressive Imaging
• CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement
• Do Noises Bother Human and Neural Networks In the Same Way? A Medical Image Analysis Perspective
• Variational Multiscale Nonparametric Regression: Algorithms and Implementation
• Channel Estimation for Large Intelligent Surface Aided MISO Communications: From LMMSE to Deep Learning Solutions
• Neural Imaging Pipelines - the Scourge or Hope of Forensics?
• Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoising
• Causal-Ex: Causal Graph-based Micro and Macro Expression Spotting
• NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Dataset and Study
• Deep Likelihood Network for Image Restoration with Multiple Degradation Levels
• Super-resolving Compressed Images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement
• Adversarial Purification through Representation Disentanglement
• A Group Variational Transformation Neural Network for Fractional Interpolation of Video Coding
• Accurate 2D Reconstruction for PET Scanners based on the Analytical White Image Model
• Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors
• Blind Image Restoration with Flow Based Priors
• Accurate Spectral Super-resolution from Single RGB Image Using Multi-scale CNN
• W2S: Microscopy Data with Joint Denoising and Super-Resolution for Widefield to SIM Mapping
• Real-Time Super-Resolution Imaging System Based on Zero-Shot Learning for Infrared Non-Destructive Testing
• Inverse mapping of face GANs
• Gated Texture CNN for Efficient and Configurable Image Denoising
• Adaptive noise imitation for image denoising
• Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution
• Blind Image Super-Resolution with Spatial Context Hallucination
• Network Architecture Search for Face Enhancement
• Deep Denoising of Flash and No-Flash Pairs for Photography in Low-Light Environments
• Distributed Deep Learning for Medical Image Denoising with Data Obfuscation
• Scale-wise Convolution for Image Restoration
• CISRDCNN: Super-resolution of compressed images using deep convolutional neural networks
• A Plug-and-Play Priors Framework for Hyperspectral Unmixing
• Multi-Block Attention for Efficient Channel Estimation in IRS-Assisted mmWave MIMO
• Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
• Leveraging Deep Stein's Unbiased Risk Estimator for Unsupervised X-ray Denoising
• Improved low-count quantitative PET reconstruction with an iterative neural network
• KRNET: Image Denoising with Kernel Regulation Network
• Learning Priors in High-frequency Domain for Inverse Imaging Reconstruction
• Seeing through a Black Box: Toward High-Quality Terahertz TomographicImaging via Multi-Scale Spatio-Spectral Image Fusion
• Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion
• Group Sparsity Residual with Non-Local Samples for Image Denoising
• Dynamic Slimmable Denoising Network
• Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention
• IMNet: A Learning Based Detector for Index Modulation Aided MIMO-OFDM Systems
• Coupled-Projection Residual Network for MRI Super-Resolution
• Towards Safer Transportation: a self-supervised learning approach for traffic video deraining
• Learning Model-Blind Temporal Denoisers without Ground Truths
• Two Heads Better than One: Dual Degradation Representation for Blind Super-Resolution
• MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
• Multiscale Sparsifying Transform Learning for Image Denoising
• Stabilizing RED using the Koopman Operator
• Multispectral CT Denoising via Simulation-Trained Deep Learning: Experimental Results at the ESRF BM18
• Assessing the performance of CT image denoisers using Laguerre-Gauss Channelized Hotelling Observer for lesion detection
• Overcoming Distribution Shifts in Plug-and-Play Methods with Test-Time Training
• LineCounter: Learning Handwritten Text Line Segmentation by Counting
• Hybrid Training of Denoising Networks to Improve the Texture Acutance of Digital Cameras
• Analysis of blurring due to short T2 decay at different resolutions in 23Na MRI
• Concurrently Extrapolating and Interpolating Networks for Continuous Model Generation
• Real-time Linear Operator Construction and State Estimation with the Kalman Filter
• Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
• High-Frequency aware Perceptual Image Enhancement
• Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services
• Human-Aware Motion Deblurring
• SSCAN: A Spatial-spectral Cross Attention Network for Hyperspectral Image Denoising
• Collaborative Filtering-Based Method for Low-Resolution and Details Preserving Image Denoising
• Noise Robust Generative Adversarial Networks
• Details Preserving Deep Collaborative Filtering-Based Method for Image Denoising
• Infusing Learned Priors into Model-Based Multispectral Imaging
• Boosting the Performance of Plug-and-Play Priors via Denoiser Scaling
• Investigating Customization Strategies and Convergence Behaviors of Task-specific ADMM
• Joint Optical Neuroimaging Denoising with Semantic Tasks
• Equivariant plug-and-play image reconstruction
• Weeping and Gnashing of Teeth: Teaching Deep Learning in Image and Video Processing Classes
• Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement
• Functional Neural Networks for Parametric Image Restoration Problems
• Self-Verification in Image Denoising
• Few-Shot Meta-Denoising
• Pyramid Real Image Denoising Network
• Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
• Image Denoising by Gaussian Patch Mixture Model and Low Rank Patches
• Legacy Photo Editing with Learned Noise Prior
• Distribution Conditional Denoising: A Flexible Discriminative Image Denoiser
• Image Denoising for Strong Gaussian Noises With Specialized CNNs for Different Frequency Components
• Layer Decomposition Learning Based on Gaussian Convolution Model and Residual Deblurring for Inverse Halftoning
• SUREMap: Predicting Uncertainty in CNN-based Image Reconstruction Using Stein's Unbiased Risk Estimate
• Enhancing Quality for VVC Compressed Videos by Jointly Exploiting Spatial Details and Temporal Structure
• Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network
• A Research and Strategy of Remote Sensing Image Denoising Algorithms
• GIID-Net: Generalizable Image Inpainting Detection via Neural Architecture Search and Attention
• Optimal Combination of Image Denoisers
• Exploring ensembles and uncertainty minimization in denoising networks
• Deep Iteration Assisted by Multi-level Obey-pixel Network Discriminator (DIAMOND) for Medical Image Recovery
• Perceptual Image Restoration with High-Quality Priori and Degradation Learning
• Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Tasks
• Asymmetric CNN for image super-resolution
• Distributed Video Adaptive Block Compressive Sensing
• Variational Deep Image Denoising
• Searching Efficient Model-guided Deep Network for Image Denoising
• RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imaging
• Adversarial Attack on Deep Learning-Based Splice Localization
• NeuroTreeNet: A New Method to Explore Horizontal Expansion Network
• ISCL: Interdependent Self-Cooperative Learning for Unpaired Image Denoising
• Identity Enhanced Residual Image Denoising
• A Deep Optimization Approach for Image Deconvolution
• Hyperspectral Unmixing Network Inspired by Unfolding an Optimization Problem
• Model-Aware Regularization For Learning Approaches To Inverse Problems
• Robust Face Verification via Disentangled Representations
• Lattice Fusion Networks for Image Denoising
• Block-matching in FPGA
• Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images
• Event Enhanced High-Quality Image Recovery
• Multi-Scale Deep Compressive Sensing Network
• Dynamic Low-light Imaging with Quanta Image Sensors
• Learning Deep Image Priors for Blind Image Denoising
• Across-domains transferability of Deep-RED in de-noising and compressive sensing recovery of seismic data
• A Convolutional Neural Networks Denoising Approach for Salt and Pepper Noise
• Image denoising by Super Neurons: Why go deep?
• Low-Light Maritime Image Enhancement with Regularized Illumination Optimization and Deep Noise Suppression
• AnciNet: An Efficient Deep Learning Approach for Feedback Compression of Estimated CSI in Massive MIMO Systems
• A Critical Analysis of Patch Similarity Based Image Denoising Algorithms
• Memory-Efficient Hierarchical Neural Architecture Search for Image Restoration
• Mixed Noise Removal with Pareto Prior
• Exploiting Temporal Attention Features for Effective Denoising in Videos
• Convolutional Nonlinear Dictionary with Cascaded Structure Filter Banks
• TreeGCN-ED: Encoding Point Cloud using a Tree-Structured Graph Network
• Video-based Point Cloud Compression Artifact Removal
• Neural Camera Simulators
• Single Frame Deblurring with Laplacian Filters
• Dense-Sparse Deep Convolutional Neural Networks Training for Image Denoising
• Binarized Weight Error Networks With a Transition Regularization Term
• Denoising convolutional neural networks for photoacoustic microscopy
• ERNet Family: Hardware-Oriented CNN Models for Computational Imaging Using Block-Based Inference
• Attention Mechanism Enhanced Kernel Prediction Networks for Denoising of Burst Images
• Generative Model for Heterogeneous Inference
• SDCNet: Smoothed Dense-Convolution Network for Restoring Low-Dose Cerebral CT Perfusion
• Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising
• Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking
• Fast and Flexible Image Blind Denoising via Competition of Experts
• FM2S: Towards Spatially-Correlated Noise Modeling in Zero-Shot Fluorescence Microscopy Image Denoising
• Deep priors for satellite image restoration with accurate uncertainties
• Visual Illusions Also Deceive Convolutional Neural Networks: Analysis and Implications
• Deep Learning Meets SAR
• Imitation Game for Adversarial Disillusion with Chain-of-Thought Reasoning in Generative AI
• Spatial-Frequency Domain Nonlocal Total Variation for Image Denoising
• Blind Denoising Autoencoder
• Encoding in the Dark Grand Challenge: An Overview
• Networks with pixels embedding: a method to improve noise resistance in images classification
• Recovery of surfaces and functions in high dimensions: sampling theory and links to neural networks
• Learning Camera-Aware Noise Models
• Enhancing and Learning Denoiser without Clean Reference
• Zero-Shot Denoising for Fluorescence Lifetime Imaging Microscopy with Intensity-Guided Learning
• Permutation invariance and uncertainty in multitemporal image super-resolution
• Very-Long Baseline Interferometry Imaging with Closure Invariants using Conditional Image Diffusion
• Investigating Image Applications Based on Spatial-Frequency Transform and Deep Learning Techniques
• Xenon Signal Denoising via Supervised, Semi-Supervised, and Unsupervised Models
• Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks
• Dirty Pixels: Towards End-to-End Image Processing and Perception