Image Denoising

Ask about this topic

Overview

Image denoising estimates the underlying scene from measurements corrupted by sensor noise, low light, or acquisition effects, supporting clearer images and reliable downstream analysis. Methods range from variational and diffusion-equation models and nonlocal patch filtering to CNNs, transformers, and generative diffusion models. Because clean targets are often scarce, many approaches use self-supervision, noise modeling, or physical knowledge of the imaging process, with tests spanning natural photographs, medical scans, and scientific images. A central challenge is suppressing noise without erasing fine detail or inventing structure, while maintaining robustness to real-world noise and practical limits on computation.

Latest papers

CardsList

157 papers14 papers in the last four weeks, up 17% on the four weeks before. 0.1% of all new papers.

  1. Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising

    Feb 19, 2026Yuduo Guo, Hao Zhang, Mingyu Li +10Image DenoisingSelf-Supervised Image Denoising

    Department of Automation, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China · Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing, China · Department of Astronomy, Tsinghua University, Beijing, China +6

  2. Denoising the Deep Sky: Physics-Based CCD Noise Formation for Astronomical Imaging

    Jan 30, 2026Shuhong Liu, Xining Ge, Ziying Gu +7Synthetic Data AugmentationImage Denoising

    The University of Tokyo · I2WM · Shanghai Astronomical Observatory +2

  3. A Machine Learning-Driven Solution for Denoising Inertial Confinement Fusion Images

    Nov 20, 2025Asya Y. Akkus, Bradley T. Wolfe, Pinghan Chu +7AutoencodersImage Denoising

    This work was conducted under the auspices of the DOE SULI and Los Alamos National Laboratory LDRD programs and by LLNL under Contract DE-AC52-07NA27344.

  4. Adaptive double-phase Rudin--Osher--Fatemi denoising model

    Oct 5, 2025Wojciech Górny, Michał Łasica, Alexandros MatsoukasImage Denoising

    Faculty of Mathematics, Universität Wien, Oskar-Morgerstern-Platz 1, 1090 Vienna, Austria; and Faculty of Mathematics, Informatics and Mechanics, University of Warsaw, Banacha 2, 02-097 Warsaw, Poland · Institute of Mathematics of the Polish Academy of Sciences, ´Sniadeckich 8, 00-656 Warsaw, Poland · Department of Mathematics, School of Applied Mathematical and Physical Sciences, National Technical University of Athens, Zografou Campus, 157 80 Athens, Greece

  5. A Tunable Despeckling Neural Network Stabilized via Diffusion Equation

    Nov 24, 2024Yi Ran, Zhichang Guo, Jia Li +3Adversarial RobustnessAlgorithm Unrolling

    School of Mathematics, Harbin Institute of Technology, 150001 Harbin, China · Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY, 22607 Hamburg, Germany · Fachbereich Mathematik, Universität Hamburg, 20146 Hamburg, Germany

  6. An Improved Variational Method for Image Denoising

    Oct 3, 2024Jing-En Huang, Jia-Wei Liao, Ku-Te Lin +2TV RegularizationImage Denoising

    National Yang Ming Chiao Tung University · National Taiwan University · National Central University +1

  7. An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations

    Jul 1, 2024Weimin Bai, Yifei Wang, Wenzheng Chen +1Expectation-MaximizationDiffusion-Based Inverse Problems

    Academy for Advanced Interdisciplinary Studies, Peking University · College of Future Technology, Peking University · National Biomedical Imaging Center, Peking University +3