On normalization-equivariance properties of supervised and unsupervised denoising methods: a survey
Not on the map. Why?
Abstract (arXiv)
Image denoising is probably the oldest and still one of the most active research topic in image processing. Many methodological concepts have been introduced in the past decades and have improved performances significantly in recent years, especially with the emergence of convolutional neural networks and supervised deep learning. In this paper, we propose a survey of guided tour of supervised and unsupervised learning methods for image denoising, classifying the main principles elaborated during this evolution, with a particular concern given to recent developments in supervised learning. It is conceived as a tutorial organizing in a comprehensive framework current approaches. We give insights on the rationales and limitations of the most performant methods in the literature, and we highlight the common features between many of them. Finally, we focus on on the normalization equivariance properties that is surprisingly not guaranteed with most of supervised methods. It is of paramount importance that intensity shifting or scaling applied to the input image results in a corresponding change in the denoiser output.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 62 of its 150 references that are in the map. First posted on arXiv 23 Feb 2024.
Builds on
62 of 150 references.
References · 62
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2022A ConvNet for the 2020scited by 3,579
- 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
- 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
- 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
38 more
- 2016Group Equivariant Convolutional Networkscited by 1,165
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
- 2017Deep Image Priorcited by 1,098
- 2021E(n) Equivariant Graph Neural Networkscited by 965
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
- 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
- 2022Simple Baselines for Image Restorationcited by 708
- 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
- 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
- 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
- 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
- 2018Rotation Equivariant CNNs for Digital Pathologycited by 422
- 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
- 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 364
- 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 307
- 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 276
- 2018Unprocessing Images for Learned Raw Denoisingcited by 250
- 2019Residual Non-local Attention Networks for Image Restorationcited by 236
- 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 213
- 2017Benchmarking Denoising Algorithms with Real Photographscited by 209
- 2022Patches Are All You Need?cited by 201
- 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 195
- 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 194
- 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
- 2019Universal Invariant and Equivariant Graph Neural Networkscited by 183
- 2019Real Image Denoising with Feature Attentioncited by 176
- 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
- 2018Non-Local Recurrent Network for Image Restorationcited by 160
- 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 126
- 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 113
- 2016Rotation equivariant vector field networkscited by 99
- 2018Neural Nearest Neighbors Networkscited by 98
- 2019Robust and interpretable blind image denoising via bias-free convolutional neural networkscited by 90
- 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 86
- 2019DeepRED: Deep Image Prior Powered by REDcited by 85
- 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
- 2018Image Restoration using Total Variation Regularized Deep Image Priorcited by 65
- 2019A Bayesian Perspective on the Deep Image Priorcited by 52
50 most cited of 62 All 62 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.