Papers with code in image denoising
-
- Some Classic networks
- 2D image denoising
- Video denoising
- ★HSI denoising
- Papers with code in other field
- 以下是用matlab实现的network
- noise estimation
- HSI Super-Resolution using Pytorch
Some Classic networks
- ResNet:Deep Residual Learning for Image Recognition
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- FCN:Fully Convolutional Networks for Semantic Segmentation
- DeepLab V3+:Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
2D image denoising
1. https://github.com/wenbihan/reproducible-image-denoising-state-of-the-art
2. https://paperswithcode.com/task/image-denoising
补充:https://github.com/z-bingo/awesome-image-denoising-state-of-the-art
benchmark: https://noise.visinf.tu-darmstadt.de/benchmark/
- NLM:A non-local algorithm for image denoising (CVPR 2005), Buades et al.
- KSVD:Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries (TIP 2006), Elad et al.
- BM3D:Image restoration by sparse 3D transform-domain collaborative filtering (SPIE Electronic Imaging 2008), Dabov et al.
- SAIST:Nonlocal image restoration with bilateral variance estimation: a low-rank approach (TIP2013), Dong et al.
- Optimal inversion of the Anscombe and Generalized Anscombe variance-stabilizing transformations(2013)
- WNNM:Weighted Nuclear Norm Minimization with Application to Image Denoising (CVPR2014), Gu et al.
- TNRD:Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration (TPAMI 2016), Chen et al.
- Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections (NIPS2016), Mao et al. 或地址
- DnCNN:Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP2017), Zhang et al. 测试成功,有训练代码
- IRCNN:Learning Deep CNN Denoiser Prior for Image Restoration(CVPR2017) 测试成功
- MemNet: A Persistent Memory Network for Image Restoration (ICCV2017), Tai et al. 测试失败,caffe多错,尝试pytorch或tensorflow版
- NLNet:Non-Local Color Image Denoising with Convolutional Neural Networks (CVPR 2017), Lefkimmiatis. 测试失败
- Beyond Deep Residual Learning for Image Restoration: Persistent Homology-Guided Manifold Simplification(2017)或:Python地址 测试成功
- xUnit: Learning a Spatial Activation Function for Efficient Image Restoration (CVPR 2018), Kligvasser et al.
- UDNet:Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018), Lefkimmiatis. 有训练代码,结果很奇怪,后面报错
- Wavelet-CNN:Multi-level Wavelet-CNN for Image Restoration (CVPR 2018), Liu et al. 测试成功,有训练代码,训练成功
- FFDNet:Toward a Fast and Flexible Solution for CNN-Based Image Denoising (TIP 2018), Zhang et al. 测试成功,有训练代码
- DIP:Deep Image Prior (CVPR 2018), Ulyanov et al.
- NLRN:Non-Local Recurrent Network for Image Restoration (NIPS 2018), Liu et al.
- RDN+:Residual Dense Network for Image Super-Resolution(CVPR 2018), Zhang et al.
- IRN:Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks (ECCV 2018), Lefkimmiatis.
- Neural Nearest Neighbors Networks (NIPS 2018), Plotz et al.
- FC-AIDE:Fully Convolutional Pixel Adaptive Image Denoiser (ICCV 2019), Cha et al.
- FOCNet: A Fractional Optimal Control Network for Image Denoising (CVPR 2019), Jia et al. 测试成功,有训练代码,训练成功
- Enhanced CNN for image denoising(2019)
- [VDNet] Variational Denoising Network: Toward Blind Noise Modeling and Removal (NeurIPS, 2019) 有训练代码
- Self-Guided Network for Fast Image Denoising(2019) 有训练代码,测试失败
- Fast Image Restoration with Multi-bin Trainable Linear Units
- Multi-level wavelet convolutional neural networks(2019) 有训练代码
- [CBDNet] Toward Convolutional Blind Denoising of Real Photographs (CVPR2019), Guo et al. 测试成功,训练代码(训练失败,缺数据文件),部分数据效果好
- Real Image Denoising with Feature Attention (ICCV2019), Anwar and Barnes.
- High-Quality Self-Supervised Deep Image Denoising (NIPS2019), Laine et al.
- Denoising Prior Driven Deep Neural Network for Image Restoration 有训练代码
- Pyramid Real Image Denoising Network(2019) 有训练代码
- RC-Net:Image Restoration Using Deep Regulated Convolutional Networks matlab
- Unprocessing Images for Learned Raw Denoising(CVPR2019)
- Residual Non-local Attention Networks for Image Restoration(ICLR2019)
- Densely Connected Hierarchical Network for Image Denoising(CVPRW2019)
- Texture variation adaptive image denoising with nonlocal PCA(2019) 3D4D版本
- Python实现的代码大部分需要自己整理训练数据集
- Self2Self With Dropout: Learning Self-Supervised Denoising From Single Image(CVPR2020)
- Transfer Learning From Synthetic to Real-Noise Denoising With Adaptive Instance Normalization(CVPR2020)
- CycleISP Real Image Restoration via Improved Data Synthesis(CVPR2020)
- Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring(CVPR2020)
- A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising(CVPR2020)
- Learning Invariant Representation for Unsupervised Image Restoration(CVPR2020)
- Unpaired Learning of Deep Image Denoising(ECCV2020) 有训练代码
- Dual Adversarial Network Toward Real-world Noise Removal and Noise Generation(ECCV2020) 有训练代码
- Spatial-Adaptive Network for Single Image Denoising(ECCV2020) 有训练代码
- Practical Deep Raw Image Denoising on Mobile Device(ECCV2020)
- PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration(ECCV2020)
- Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration(ECCV2020)
- Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation(ECCV2020)
- Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks(ECCV2020)
- Burst Denoising via Temporally Shifted Wavelet Transforms(ECCV2020)
- Learning Enriched Features for Real Image Restoration and Enhancement(ECCV2020)
- Fully Trainable and Interpretable Non-Local Sparse Models for Image Restoration(ECCV2020)
- Microscopy Image Restoration with Deep Wiener-Kolmogorov Filters(ECCV2020)
- End-to-End Unpaired Image Denoising with Conditional Adversarial Networks(AAAI2020)
- Scale-Wise Convolution for Image Restoration(AAAI2020)
- Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising(NeurIPS2020)
- Neural Sparse Representation for Image Restoration(NeurIPS2020)
- CLEARER: Multi-Scale Neural Architecture Search for Image Restoration(NeurIPS2020) 有训练代码,测试失败(缺文件)
- NTGAN: Learning Blind Image Denoising without Clean Reference(2020)
- Attention-guided CNN for image denoising(2020) Python2
- Pyramid Attention Networks for Image Restoration 有训练代码,数据集很大,需要下载,针对彩色图像去噪
- Image denoising using deep CNN with batch renormalization(2020) 不知道运行哪个
- Plug-and-Play Image Restoration with Deep Denoiser Prior(2020) 测试成功,训练代码为FFDNet的修改
- Designing and Training of A Dual CNN for Image Denoising(2020) 未公布
- Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising(2020) 测试成功
- Connecting Image Denoising and High-Level Vision Tasks via Deep Learning
- Graph Convolutional Networks for Learning with Few Clean and Many Noisy Labels
- Deep Graph-Convolutional Image Denoising Python2
- BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration
- CFMNet:Flexible Image Denoising with Multi-layer Conditional Feature Modulation 有训练代码,测试失败,缺乏数据集
- Gated Texture CNN for Efficient and Configurable Image Denoising
- Densely Self-guided Wavelet Network for Image Denoising(CVPRW) 有训练代码
- Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image(2020TIP) 有训练代码
- Flashlight CNN Image Denoising
- Color Image Restoration Exploiting Inter-channel Correlation with a 3-stage CNN(2020)
- Distillating Knowledge from Original Network and Siamese Network for Real Image Denoising
- [FAN] Frequency Attention Network: Blind Noise Removal for Real Images, ACCV, 2020
- Multilevel Edge Features Guided Network for Image Denoising
- DUBD:Deep Universal Blind Image Denoising(2021)
- Quantum mechanics-based signal and image representation: application to denoising
- Adversarial Training for Solving Inverse Problems in Image Processing(2021) 有训练代码
- MPRNet:Multi-Stage Progressive Image Restoration(CVPR2021) 有训练代码
- Pre-Trained Image Processing Transformer(CVPR2021)
- Auto-Exposure Fusion for Single-Image Shadow Removal(CVPR2021)
- Plug-and-Play external and internal priors for image restoration(未更新)
- A support-denoiser-driven framework for single image restoration(2021)
- A Residual Dense U-Net Neural Network for Image Denoising(2021)
- A Noise-Robust Online Convolutional Coding Model and Its Applications to Poisson Denoising and Image Fusion
- Efficient Deep Image Denoising via Class Specific Convolution
- COLA-Net: Collaborative Attention Network for Image Restoration
- Minimum unbiased risk estimate based 2DPCA for color image denoising(2021)
- An Unsupervised deep learning approach for real-world image denoising(ICLR2021)
- GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Images(ICLR2021)
- NBNet: Noise Basis Learning for Image Denoising with Subspace Projection(CVPR2021) 或地址
- High Perceptual Quality Image Denoising with a Posterior Sampling CGAN(2021)
- Variational Deep Image Denoising(2021)
- Median Filter Aided CNN Based Image Denoising An Ensemble Aprroach
- Training a Better Loss Function for Image Restoration
- A new blind image denoising method based on asymmetric generative adversarial network
- Dilated kernel prediction network for single-image denoising
- Invertible Denoising Network: A Light Solution for Real Noise Removal(CVPR2021)
- Blind microscopy image denoising with a deep residual and multiscale encoder/decoder network
- HINet: Half Instance Normalization Network for Image Restoration
- Beyond Joint Demosaicking and Denoising: An Image Processing Pipeline for a Pixel-bin Image Sensor(2021CVPRW)
- Deep Convolutional Dictionary Learning for Image Denoising(CVPR2021)
- Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images(CVPR2021)
- New: Neighbor2Neighbor: A Self-Supervised Framework for Deep Image Denoising 2022TIP
- Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network 未公布
- BoostNet: A Boosted Convolutional Neural Network for Image Blind Denoising
- Image Restoration via Reconciliation of Group Sparsity and Low-Rank Models(2021TIP)
- FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noise(CVPR2021)
- Uformer: A General U-Shaped Transformer for Image Restoration 重点研究!!
- DRNet: A Deep Neural Network With Multi-Layer Residual Blocks Improves Image Denoising
- ICCV2021:Rethinking Deep Image Prior for Denoising
- ICCV2021:Spatially-Adaptive Image Restoration using Distortion-Guided Networks
- SwinIR: Image Restoration Using Swin Transformer 重点研究!!
- Restormer: Efficient Transformer for High-Resolution Image Restoration
- U^2 -Former: A Nested U-shaped Transformer for Image Restoration
- On Efficient Transformer and Image Pre-training for Low-level Vision
- Exploiting Non-Local Priors via Self-Convolution For Highly-Efficient Image Restoration
- Fast and High-Quality Image Denoising via Malleable Convolutions(2022)
- IDEA-Net: Adaptive Dual Self-Attention Network for Single Image Denoising(WACV2022)
- Deep Image Denoising with Adaptive Priors
- Simple Baselines for Image Restoration
- Decomposed Neural Architecture Search for Image Denoising
- NHNet: A Non-Local Hierarchical Network for Image Denoising
- Robust Deep Ensemble Method for Real-world Image Denoising
- Variational Deep Image Restoration
Video denoising
- A non-local CNN for video denoising(2019)
- ViDeNN: Deep Blind Video Denoising(CVPR2019)
- Model-blind video denoising via frame-to-frame training(CVPR2019)
- Learning Deformable Kernels for Image and Video Denoising(2019)
- FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation(CVPR2020)
- Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes(CVPR2020)
- Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising(2020)
- Self-supervised training for blind multi-frame video denoising(2021)
- Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask(2021)
- ICCV2021:Deep Reparametrization of Multi-Frame Super-Resolution and Denoising(无代码)
★HSI denoising
HSI:https://github.com/junjun-jiang/Hyperspectral-Image-Denoising-Benchmark
Global Correlation along Spetrum(GCS),Non-local Self Similarity(NSS)
ICVL数据集:http://icvl.cs.bgu.ac.il/hyperspectral/
http://lesun.weebly.com/hyperspectral-data-set.html
WDC华盛顿地址:https://engineering.purdue.edu/~biehl/MultiSpec/hyperspectral.html
数据集大全:https://rslab.ut.ac.ir/data
- [LRTA] Denoising and Dimensionality Reduction Using Multilinear Tools for Hyperspectral Images(2008) 测试成功
- [PARAFAC] Denoising of hyperspectral images using the PARAFAC model and statistical performance analysis(2012) 测试成功,效果较差
- [TDL] Decomposable nonlocal tensor dictionary learning for multispectral image denoising, CVPR2014, P. Yi et al. 测试成功
- [LRMR] Hyperspectral image restoration using low-rank matrix recovery, TGRS2014, H. Zhang et al. 测试成功,比较久,需要调参
- [NAILRMA] Hyperspectral Image Denoising via Noise-Adjusted Iterative Low-Rank Matrix Approximation, JStars2015, H. Zhang et al 测试成功,需要调参
- [SR+LRC] Hyperspectral image denoising via sparse representation and low-rank constraint, TGRS2015, Y. Zhao et al. 测试失败
- [ITSReg] Multispectral images denoising by intrinsic tensor sparsity regularization, CVPR2016, Q. Xie et al. 测试成功
- [LRTV] Total-variation-regularized low-rank matrix factorization for hyperspectral image restoration(2016) 测试成功
- [WSNM] Hyperspectral image restoration via iteratively regularized weighted schatten p-norm minimization(2016)
- [LLRT] Hyper-Laplacian Regularized Unidirectional Low-rank Tensor Recovery for Multispectral Image Denoising, CVPR2017, Y. Chang et al或:地址 测试成功
- [GLF] Hyperspectral image denoising based on global and non-local low-rank factorizations(2017)
- [LR] Hyperspectral image denoising and anomaly detection based on low-rank and sparse representations(2017)
- [NMoG] Denoising Hyperspectral Image with Non-i.i.d. Noise Structure, IEEE TCYB2017, Y. Chen et al. 测试成功
- [LLRGTV/LLRSSTV] Hyperspectral Image Denoising Using Local Low-Rank Matrix Recovery and Global Spatial-Spectral Total Variation(2018) 测试成功
- [FastHyDe] Fast hyperspectral image denoising and inpainting based on low-rank and sparse representations, J-STARS2018, L. Zhuang et al. 测试成功
- Hyperspectral Image Restoration under Complex Multi-Band Noises(2018)
- [LRTDTV] Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition(2018)或:地址 测试成功
- [HSID-CNN] Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network, TGRS2018, Q. Yuan et al. 测试成功,但caffe多坑,尝试pytorch或tensorflow版本(github上都有)
- HSI-DeNet: Hyperspectral image restoration via convolutional neural network(2018)
- [SNLRSF] Hyperspectral Image Denoising via Subspace-Based Nonlocal Low-Rank and Sparse Factorization(2019)
- [LR] Mixed Noise Removal in Hyperspectral Image via Low-Fibered-Rank Regularization(2019)或:地址
- [Tensor] Color Image and Multispectral Image Denoising Using Block Diagonal Representation, arXiv2019, Zhaoming Kong et al.
- Hyperspectral Image Denoising using Dictionary Learning(2019)
- [LRTDGS] Hyperspectral Image Restoration Using Weighted Group Sparsity-Regularized Low-Rank Tensor Decomposition
- [NGmeet] Non-local Meets Global: An Integrated Paradigm for Hyperspectral Denoising. CVPR. 2019 测试成功,参数比较多
- [DHP] Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution, arxiv2019, Oleksii Sidorov et al.
- [DD-CNN] Hyperspectral Image Denoising With Dual Deep CNN 测试成功,但效果不太好
- [SSGN] Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network(未更新)
- [DSSRL] Deep Spatial-spectral Representation Learning for Hyperspectral Image Denoising, IEEE TCI 2019, Weisheng Dong et al. 测试失败:Unable to open object (object ‘train_input’ doesn’t exist),TF1版本太旧了
- [SDeCNN] A Single Model CNN for Hyperspectral Image Denoising(2019) 有训练代码,训练非常久(考虑更改学习率),测试成功,非常重要!在此基础上改进!
- Zero-Shot Hyperspectral Image Denoising With Separable Image Prior
- [QRNN3D] 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising(2020) 训练集非常多且需要手动下载,非常重要!在此基础上改进!
- [E-3DTV] Enhanced 3DTV Regularization and Its Applications on HSI Denoising and Compressed Sensing(2020)或:地址
- Hyperspectral Mixed Noise Removal By ℓ1-Norm-Based Subspace Representation(2020)
- [DSSBP] Deep Spatio-Spectral Bayesian Posterior for Hyperspectral Image Non-i.i.d. Noise Removal(未更新)
- [WLRTR] Weighted low-rank tensor recovery for hyperspectral image restoration(2020)
- A Tensor Subspace Representation Method for Hyperspectral Image Denoising(2020)
- [LTDL] A low-rank tensor dictionary learning method for hyperspectral image denoising(2020)
- [LRTF-DFR] Double Factor-Regularized Low-Rank Tensor Factorization for Mixed Noise Removal in Hyperspectral Image(2020)
- Hyperspectral Image Restoration: Where Does the Low-Rank Property Exist(2020)
- [ENCAM] Enhanced Non-Local Cascading Network with Attention Mechanism for Hyperspectral Image Denoising(2020)
- [MsDUC] Fast stripe noise removal from hyperspectral image via multi-scale dilated unidirectional convolution(2020) 测试失败
- A New Multi-Scale Residual Learning Network for HSI Inconsistent Noise Removal(未更新)
- Hyperspectral Image Denoising Using SURE-Based Unsupervised Convolutional Neural Networks Tensorflow 2.0 跑一下!
- Hyperspectral Image Restoration by Tensor Fibered Rank Constrained Optimization and Plug-And-Play Regularization(2021)
- Uncertainty Quantification of Hyperspectral Image Denoising Frameworks Based on Sliding-Window Low-Rank Matrix Approximation(2021) matlab
- Thermal Hyperspectral Image Denoising Using Total Variation Based on Bidirectional Estimation and Brightness Temperature Smoothing(2021)
- A Graph-regularized Non-local Hyperspectral Image Denoising Method(2021) matlab
- Deep Spatial-Spectral Global Reasoning Network for Hyperspectral Image Denoising(2021) 已公布!跑一次!
- Learning An Explicit Weighting Scheme for Adapting Complex HSI Noise(CVPR2021) 论文地址
- Adaptive Hyperspectral Mixed Noise Removal
- 综合:https://drive.google.com/drive/folders/1BxlOTwKXb8VvgPCB3QufnTnaTAjWMLAk
Papers with code in other field
- SSR-NET: Spatial–Spectral Reconstruction Network for Hyperspectral and Multispectral Image Fusion
- MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion
- [ ]
- Few-shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning
- Graph Convolutional Networks for Hyperspectral Image Classification
- Hyperspectral Image Classification with Feature-Oriented Adversarial Active Learning
- HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers(2020)
- SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation(2021)
- Spatial-Spectral Transformer for Hyperspectral Image Classification(2021) 未公布
- [ ]
- Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution(ECCV2020)
- Model-Guided Deep Hyperspectral Image Super-resolution(2021)
- Spectral Response Function-Guided Deep Optimization-Driven Network for Spectral Super-Resolution(2021)
- [ ]
- No-Reference Hyperspectral Image Quality Assessment via Quality-Sensitive Features Learning
- [ ]
- Convolutional Two-Stream Generative Adversarial Network-Based Hyperspectral Feature Extraction(2021 注:有SVM分类代码)
- [ ]
以下是用matlab实现的network
- Hyperspectral Image Classification via a Random Patches Network
- Hyperspectral Image Classification with Convolutional Neural Network and Active Learning
- Deep supervised learning for hyperspectral data classification through convolutional neural networks
- Hyperspectral Image Classification With Deep Feature Fusion Network
- Deep Hashing Neural Networks for Hyperspectral Image Feature Extraction
- Multichannel Pulse-Coupled Neural Network-Based Hyperspectral Image Visualization
- Regularizing Hyperspectral and Multispectral Image Fusion by CNN Denoiser
noise estimation
- Noise Level Estimation Using Weak Textured Patches of a Single Noisy Image(2012)
- Image Noise Level Estimation by Principal Component Analysis(2013)
- An Efficient Statistical Method for Image Noise Level Estimation(2015)
HSI Super-Resolution using Pytorch
- 2021 Hyperspectral Image Super-resolution via Deep Spatio-spectral Attention Convolutional Neural Networks
欢迎补充~