Data to 14 Oct 2026

High-Quality Self-Supervised Deep Image Denoising

arXiv 1901.10277 ↗First posted 29 Jan 2019cs.LG cs.CV cs.NEcited by 161

Not on the map. Why?

Abstract (arXiv)

We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can thus be applied in situations where such data is unacceptably expensive or impossible to acquire. We build on a recent technique that removes the need for reference data by employing networks with a "blind spot" in the receptive field, and significantly improve two key aspects: image quality and training efficiency. Our result quality is on par with state-of-the-art neural network denoisers in the case of i.i.d. additive Gaussian noise, and not far behind with Poisson and impulse noise. We also successfully handle cases where parameters of the noise model are variable and/or unknown in both training and evaluation data.

Key facts. Cited by 161 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 36; 2022: 36; 2023: 31; 2024: 23; 2025: 18; 2026: 16.

161 papers.

Sort:

By area:

2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 173
2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 113
2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 93
2022Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spotscited by 84
2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 61
2021SSH: A Self-Supervised Framework for Image Harmonizationcited by 60
2022C2N: Practical Generative Noise Modeling for Real-World Denoisingcited by 56
2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Modelscited by 51
2024RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Modelscited by 43
2021Rethinking Deep Image Prior for Denoisingcited by 38

38 more

2023LG-BPN: Local and Global Blind-Patch Network for Self-Supervised Real-World Denoisingcited by 37
2021IDR: Self-Supervised Image Denoising via Iterative Data Refinementcited by 36
2023Neural Preset for Color Style Transfercited by 36
2021A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restorationcited by 34
2023Spatially Adaptive Self-Supervised Learning for Real-World Image Denoisingcited by 33
2023Random Sub-Samples Generation for Self-Supervised Real Image Denoisingcited by 31
2021DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flowscited by 30
2023MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Networkcited by 30
2020Patch2Self: Denoising Diffusion MRI with Self-Supervised Learningcited by 29
2021Interpretable Unsupervised Diversity Denoising and Artefact Removalcited by 26
2021Optimal Transport for Unsupervised Denoising Learningcited by 24
2021FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noisecited by 22
2022Self-Supervised Representation Learning via Latent Graph Predictioncited by 22
2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 21
2021As if by magic: self-supervised training of deep despeckling networks with MERLINcited by 18
2021Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matchingcited by 18
2022Learn from Unpaired Data for Image Restoration: A Variational Bayes Approachcited by 18
2021Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancementcited by 17
2022Self-Supervised Image Restoration with Blurry and Noisy Pairscited by 17
2023Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarioscited by 17
2023Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Reviewcited by 17
2021Adaptive Denoising via GainTuningcited by 16
2021Robustness via Uncertainty-aware Cycle Consistencycited by 16
2023PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoisingcited by 16
2023Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image Denoisingcited by 15
2022Scaling Laws For Deep Learning Based Image Reconstructioncited by 14
2023Self-Supervised Image Denoising for Real-World Images with Context-aware Transformercited by 13
2022Zero-shot Blind Image Denoising via Implicit Neural Representationscited by 12
2023Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Networkcited by 12
2025IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoisingcited by 12
2022Bayesian Image Super-Resolution with Deep Modeling of Image Statisticscited by 11
2021Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoisercited by 10
2021The potential of self-supervised networks for random noise suppression in seismic datacited by 10
2021Learning to Assimilate in Chaotic Dynamical Systemscited by 10
2021Deformation-Compensated Learning for Image Reconstruction without Ground Truthcited by 9
2024Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoisingcited by 9
2025Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Datacited by 9
2023Recurrent Self-Supervised Video Denoising with Denser Receptive Fieldcited by 8

50 most cited of 161 All 161 (JSON)