Noise2Noise: Learning Image Restoration without Clean Data
read the original abstract
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans -- all corrupted by different processes -- based on noisy data only.
This paper has not been read by Pith yet.
Forward citations
Cited by 16 Pith papers
-
Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising
A2A achieves one-shot ultrasound denoising via pyramid self-contrastive learning on sub-aperture signals to disentangle anatomy from noise, yielding large SNR and CNR gains in simulations and in vivo scans.
-
FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising
FrequencyCT generates pseudo-labels via regional low-frequency anchoring, phase-preserving modulation, and high-frequency mask perturbation for self-supervised low-dose CT denoising.
-
A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis
A mixture-of-experts transformer foundation model pretrained on diverse SEM images enables generalization across materials and outperforms SOTA on unsupervised defocus-to-focus restoration.
-
Towards a Unified Theoretical Framework for Splitting-based Self-Supervised MRI Reconstruction
UNITS framework proves self-supervised splitting risk in MRI reconstruction is a weighted supervised risk, yielding identical Bayes-optimal predictors and relating training residuals to prediction bias.
-
RDDM: A Residual-Driven Drifting Model for High-Fidelity Low-Dose CT Denoising
RDDM introduces a residual drifting field with attractive and repulsive forces to achieve one-step supervised denoising of low-dose CT, reporting superior PSNR, SSIM, FID of 5.87, and 15 ms inference time.
-
TwinSpecNet: Extending APOGEE's chemical reach to low-S/N spectra via empirical paired learning
TwinSpecNet uses empirical paired learning on spectral twins to denoise low-S/N APOGEE spectra and predict stellar parameters and abundances with lower scatter than the standard pipeline.
-
TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
TM-BSN introduces triangular-masked convolutions that align blind spots with diamond-shaped noise correlations from camera demosaicing, enabling stronger self-supervised denoising at full resolution without downsampling.
-
Progressive $\mathcal{J}$-Invariant Self-supervised Learning for Low-Dose CT Denoising
A progressive J-invariant self-supervised learning framework for low-dose CT denoising outperforms prior self-supervised methods and matches some supervised ones on the Mayo dataset.
-
Linear Attention Based Deep Nonlocal Means Filtering for Multiplicative Noise Removal
LDNLM replaces the quadratic similarity and averaging steps of nonlocal means with deep convolutional feature extraction and linear attention operations to produce a linear-complexity denoiser for multiplicative noise...
-
Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
Denoising-PGD attack exposes shared adversarial samples across non-blind, blind, plug-and-play and unfolding denoisers, yielding a robustness similitude metric that ranks data-driven non-blind models as most robust.
-
Self-supervised Hyperspectral Image Restoration using Separable Image Prior
A self-supervised separable CNN trained on data synthesized from a single degraded hyperspectral image achieves restoration without clean reference images.
-
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
Machine learning methods including denoising autoencoders, unsupervised interference mitigation, blind source separation, and certifiable classification are developed and experimentally validated to improve multi-spec...
-
AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data
Unsupervised denoising methods improve faint-source detection in astronomical images from HST and CFHT, with better performance when models are initialized on similar-domain data.
-
Progressive $\mathcal{J}$-Invariant Self-supervised Learning for Low-Dose CT Denoising
A new progressive J-invariant self-supervised denoising method for LDCT that uses step-wise blind-spot enforcement and controlled noise injection outperforms prior self-supervised approaches on the Mayo dataset.
-
Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noise
DWTA-Net is a two-stage recurrent neural network for low-light video enhancement that combines Mamba-based local restoration with dynamic optical-flow-guided temporal aggregation and a texture-adaptive loss to suppres...
-
A Survey on Diffusion Models for Inverse Problems
A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.