cs.CVNov 17, 2026

SIDUMN: Self-Supervised Image Denoising Under Symmetric Multiplicative Noise

Authors: Nyan Htet Naing, Gyeongha Hwang

Organizations: Department of Mathematics, Kyungpook National University, Korea · Department of Mathematics, Yeungnam University, Korea

Abstract

Self-supervised denoising is challenging when the corruption is multiplicative and signal-dependent. In this letter, we propose SIDUMN, a symmetric noisier framework for self-supervised denoising under mean-one symmetric multiplicative noise. Given noisy observations and the noise law, the method samples an independent synthetic noise factor from the same law and constructs two complementary noisier images by applying the factor and its reflection about one. The denoising network is trained to predict one noisier image from the other, and at inference the reconstructions of KK such antithetic pairs are averaged. We show that the population target of the training loss is the clean conditional mean minus a multiplicative cross-term. We further prove that, for any trained network, antithetic averaging never increases the expected squared error of a single noisier-input reconstruction. Numerical results validate the theoretical findings and the proposed method.

Figures & tables

Explore similar work

CardsList
  1. Learning to Recorrupt: Noise Distribution Agnostic Self-Supervised Image Denoising

    Mar 26, 2026Brayan Monroy, Jorge Bacca, Julián TachellaSelf-Supervised Image DenoisingSelf-Supervised Learning

  2. 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 DenoisingSelf-Supervised Learning

  3. LoTA-N2N: Local Trace Adaptation for Zero-Shot Self-Supervised Image Denoising

    Jul 27, 2026Jintong Hu, Bin Xia, Junlin Liu +2Self-Supervised Image DenoisingSelf-Supervised Learning