paper-with-me

홈 › Papers

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

2021-12-05 · CVPR 2022 1 · Kwanyoung Kim, Taesung Kwon, Jong Chul Ye

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.

📄 PDF Abstract BibTeX arXiv:2112.03696

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage Denoising

Similar Papers 제목 키워드 기반

SSP-RACL: Classification of Noisy Fundus Images with Self-Supervised Pretraining and Robust Adaptive Credal Loss

2024-09-25 · Mengwen Ye, Yingzi Huangfu, You Li, Zekuan Yu

Fundus image classification is crucial in the computer aided diagnosis tasks, but label noise significantly impairs the performance of deep neural networks. To address this challenge, we propose a robust framework, Self-…

Clinical Knowledgeimage-classificationImage ClassificationMemorization

Self-Supervised Noise Adaptive MRI Denoising via Repetition to Repetition (Rep2Rep) Learning

2025-04-24 · Nikola Janjušević, Jingjia Chen, Luke Ginocchio, Mary Bruno 외

Purpose: This work proposes a novel self-supervised noise-adaptive image denoising framework, called Repetition to Repetition (Rep2Rep) learning, for low-field (<1T) MRI applications. Methods: Rep2Rep learning extends th…

DenoisingImage Denoising

Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning

2021-01-21 · Lang Huang, Chao Zhang, Hongyang Zhang

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervis…

Linear evaluationRepresentation LearningSelf-Supervised Learning

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

2026-03-26 · Brayan Monroy, Jorge Bacca, Julián Tachella arxiv

Self-supervised image denoising methods have traditionally relied on either architectural constraints or specialized loss functions that require prior knowledge of the noise distribution to avoid the trivial identity map…

Image Denoising

Joint self-supervised blind denoising and noise estimation

2021-02-16 · Jean Ollion, Charles Ollion, Elisabeth Gassiat, Luc Lehéricy 외

We propose a novel self-supervised image blind denoising approach in which two neural networks jointly predict the clean signal and infer the noise distribution. Assuming that the noisy observations are independent condi…

DenoisingImage DenoisingNoise Estimation