Noise Distribution Adaptive Self-Supervised Image Denoising using Tweedie Distribution and Score Matching

TL;DR

This paper introduces a novel self-supervised image denoising method leveraging Tweedie distributions and score matching, enabling noise model estimation and state-of-the-art denoising without clean references.

Contribution

It develops a distribution-independent denoising formula using Tweedie distributions, extending Noise2Score to handle various noise types without prior noise knowledge.

Findings

Accurately estimates noise models and parameters.

Achieves state-of-the-art denoising performance.

Works effectively on benchmark and real-world datasets.

Abstract

Tweedie distributions are a special case of exponential dispersion models, which are often used in classical statistics as distributions for generalized linear models. Here, we reveal that Tweedie distributions also play key roles in modern deep learning era, leading to a distribution independent self-supervised image denoising formula without clean reference images. Specifically, by combining with the recent Noise2Score self-supervised image denoising approach and the saddle point approximation of Tweedie distribution, we can provide a general closed-form denoising formula that can be used for large classes of noise distributions without ever knowing the underlying noise distribution. Similar to the original Noise2Score, the new approach is composed of two successive steps: score matching using perturbed noisy images, followed by a closed form image denoising formula via distribution-independent Tweedie's formula. This also suggests a systematic algorithm to estimate the noise model and noise parameters for a given noisy image data set. Through extensive experiments, we demonstrate that the proposed method can accurately estimate noise models and parameters, and provide the state-of-the-art self-supervised image denoising performance in the benchmark dataset and real-world dataset.