Self-Supervised Image Denoising

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 13

All topics

Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising
Sep 15, 2026Dingyan Shang, Zhenyu Xu, Youting Wang +2Self-Supervised Image Denoising Denoising Autoencoders
Independent Researcher · Frisco, USA · Fulshear, USA +3
Physics-Driven Independent Pair Generation for Iterative Self-Supervised Low-Dose CT Denoising
Sep 1, 2026Xianlei Han, Shaoyu Wang, Jiancheng Fang +2Self-Supervised Image Denoising Self-Supervised Learning
School of Mathematics and Computer Sciences, Nanchang University, Nanchang 330031, China · School of Information Engineering, Nanchang University, Nanchang 330031, China · School of Biomedical Engineering, Sun Yat-sen University, Shenzhen 510275, Guangdong, China
LoTA-N2N: Local Trace Adaptation for Zero-Shot Self-Supervised Image Denoising
Jul 27, 2026Jintong Hu, Bin Xia, Junlin Liu +2Self-Supervised Image Denoising Self-Supervised Learning
Tsinghua University · The Chinese University of Hong Kong · University of Southern California +1
Denoising ICF Images with Multiplicative Uniform Noise: A Self-Supervised Study Based on the Log-Domain Noisier2Inverse Framework
Jun 26, 2026Gyeongha Hwang, Bradley Thomas Wolfe, Naima NaheedSelf-Supervised Image Denoising Self-Supervised Learning
Department of Mathematics, Yeungnam University, Gyeongsan, Republic of Korea. · Research Technologist, P-4: Thermonuclear Plasma Physics, Los Alamos National Laboratory, Los Alamos, NM 87545, USA. · Department of Computer Science and Engineering, Benedict College, Columbia, SC 29204, USA.
NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling
Jun 22, 2026Jaehyun Cho, YoungJoon YooSelf-Supervised Image Denoising 3D Medical Imaging
Department of Artificial Intelligence, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea · SNUAILAB, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea
Physics-Guided Self-Supervised Statistical Residual Learning for Sonar Despeckling with Improved Generalization
May 23, 2026Swapna Pillai, Siddharth Singh Savner, Sujit Kumar SahooSelf-Supervised Image Denoising Self-Supervised Learning
School of Electrical Sciences, Indian Institute of Technology Goa, Goa 403401, India · Inria, Sophia Antipolis, France
Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising
May 12, 2026Jiajing Zhang, Bingze Dai, Xi Zhang +2Self-Supervised Image Denoising Test-Time Adaptation
Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong · Department of Biomedical Engineering, Duke University, North Carolina, United States
Deploying Self-Supervised Learning for Real Seismic Data Denoising
May 11, 2026Giovanny A. M. Arboleda, Claudio D. T. de Souza, Carlos E. M. dos Anjos +6Self-Supervised Image Denoising Self-Supervised Learning
COPPE Federal University of Rio de Janeiro Rio de Janeiro, Brazil · CENPES, Petrobras Rio de Janeiro, Brazil
FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising
May 11, 2026Guoquan Wei, Liu Shi, Chong Chen +1Self-Supervised Image Denoising Self-Supervised Learning
School of Information Engineering, Nanchang University, Nanchang 330031, China · SKLMS, ICMSEC, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China
Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning
May 7, 2026Qiyu Rao, Haozhe Tian, Homayoun Hamedmoghadam +1Self-Supervised Image Denoising Electroencephalography
Department of Electrical and Electronic Engineering, Imperial College London · Dyson School of Design Engineering, Imperial College London
Neighbor2Inverse: Self-Supervised Denoising for Low-Dose Region-of-Interest Phase Contrast CT
May 1, 2026Johannes B. Thalhammer, Lorenzo D'Amico, Lucy Costello +11Self-Supervised Image Denoising Computed Tomography
Chair of Biomedical Physics, Department of Physics, School of Natural Sciences, TU Munich · Munich Institute of Biomedical Engineering, TU Munich · Institute for Diagnostic and Interventional Radiology, TUM Klinikum +3
AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data
Apr 18, 2026Omid Vaheb, Sebastien Fabbro, Stark DraperSelf-Supervised Image Denoising Noise Robustness
Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, 10 King’s College Road, Toronto, ON M5S 3G4, Canada · National Research Council Herzberg Astronomy an Astrophysics Research Centre, 5071 West Saanich Road, Victoria, BC V9E 2E7, Canada · Department of Computer Science, University of British Columbia, Vancouver, BC, V6T 1Z4, Canada
Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising
Mar 26, 2026Brayan Monroy, Jorge Bacca, Julián TachellaSelf-Supervised Image Denoising Self-Supervised Learning
Universidad Industrial de Santander, Colombia · CNRS, ENS de Lyon, France

Sep 15, 2026, cs.LGJ/K move · Enter open · S save

Noise2Noise Revisited: Training Pair Distributions Dominate Loss Choice in Self-Supervised Denoising

Dingyan Shang, Zhenyu Xu, Youting Wang, Bonan Shen+1

Independent Researcher · Frisco, USA · Fulshear, USA+3

Self-Supervised Image Denoising Denoising Autoencoders Image Denoising

Open paper AskPDF arXiv

Noise2Noise (N2N) trains denoisers on pairs of independently corrupted observations, eliminating clean references. We stress-test two natural conjectures about why the L1 loss outperforms L2 here. First, the hypothesis that the L1 loss confers robustness via parameter sparsity confuses the loss with Lasso regularization: an explicit Lasso penalty produces the predicted sparsity yet fails to reproduce L1's cross-noise behavior, while L1- and L2-trained weight distributions are indistinguishable. Second, the population optima of the two losses coincide exactly for symmetric signal posteriors and nearly so for concentrated ones. Measured differences are therefore dominated by optimization dynamics (bounded-influence gradients), which we probe with gradient statistics and contaminated-target training. On Kodak24 with five synthetic noise families, the L1 loss holds a statistically significant edge over L2, below 1 dB PSNR, holding across three seeds on 13 of the 14 noise columns. On real camera noise the loss is not the decisive variable in distribution: on official SIDD validation blocks, synthetic-Gaussian-trained N2N models gain only 0.8 to 3.7 dB over the noisy input regardless of loss, while retraining on SIDD's own noisy pairs, never reading ground truth, gains 9.4 to 11.0 dB, far ahead of BM3D. All metrics are on raw network outputs, and the study makes no leaderboard claim. The training pair distribution, not the loss, carries the inductive bias. That design rule applies wherever clean references are unobtainable, from microscopy to industrial inspection sensors.

Momentum

Related topics

Latest papers 13