Implicit Neural Speckle Denoising

2026-08-06

AI Summary

This work addresses the challenge of suppressing multiplicative, spatially correlated speckle noise in dynamic coherent imaging—a task where conventional frame averaging proves ineffective. The authors propose a training-free denoising framework that integrates spatiotemporal implicit neural representation with an aperture-aware maximum likelihood model. Notably, it explicitly embeds pupil-geometry-dependent speckle covariance into the optimization process for the first time, enabling compatibility with arbitrary aperture configurations without retraining. Efficiency and scalability are achieved through matrix-free optimization accelerated by FFT, combined with stochastic approximation, conjugate gradient methods, and a no-reference automatic early-stopping criterion. Experiments demonstrate superior performance over classical, unsupervised, and supervised baselines in terms of spatial fidelity, temporal consistency, and robustness across diverse speckle statistics.

Abstract

Speckle fundamentally limits coherent imaging by introducing multiplicative, spatially correlated noise that obscures scene structure. Removing speckle noise from dynamic scenes--that do not benefit from conventional speckle averaging--is particularly challenging. We introduce a training-free framework that combines a spatiotemporal implicit neural representation with an aperture-aware maximum-likelihood formulation to recover dynamic, speckle-free imagery directly from noisy observations. The coherent likelihood explicitly models the aperture-dependent spatial covariance of speckle, enabling adaptation to arbitrary pupil geometries without retraining. A matrix-free implementation based on FFT-accelerated operators, stochastic approximations, and conjugate gradients makes optimization practical for realistic image sizes. Meanwhile, a blind holdout criterion provides automatic early stopping without clean reference data. Simulated and laboratory results demonstrate improved spatial fidelity, temporal consistency, and robustness to varying speckle statistics relative to classical, unsupervised, and supervised baselines.

Problem

• speckle denoising
• coherent imaging
• dynamic scenes
• spatially correlated noise
• multiplicative noise

Innovation

• implicit neural representation
• speckle denoising
• maximum-likelihood estimation
• aperture-aware modeling
• matrix-free optimization