Masked and Shuffled Blind Spot Denoising for Real-World Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chihaoui, Hamadi, Favaro, Paolo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910410033070080
author Chihaoui, Hamadi
Favaro, Paolo
author_facet Chihaoui, Hamadi
Favaro, Paolo
contents We introduce a novel approach to single image denoising based on the Blind Spot Denoising principle, which we call MAsked and SHuffled Blind Spot Denoising (MASH). We focus on the case of correlated noise, which often plagues real images. MASH is the result of a careful analysis to determine the relationships between the level of blindness (masking) of the input and the (unknown) noise correlation. Moreover, we introduce a shuffling technique to weaken the local correlation of noise, which in turn yields an additional denoising performance improvement. We evaluate MASH via extensive experiments on real-world noisy image datasets. We demonstrate on par or better results compared to existing self-supervised denoising methods.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09389
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Masked and Shuffled Blind Spot Denoising for Real-World Images
Chihaoui, Hamadi
Favaro, Paolo
Computer Vision and Pattern Recognition
Machine Learning
We introduce a novel approach to single image denoising based on the Blind Spot Denoising principle, which we call MAsked and SHuffled Blind Spot Denoising (MASH). We focus on the case of correlated noise, which often plagues real images. MASH is the result of a careful analysis to determine the relationships between the level of blindness (masking) of the input and the (unknown) noise correlation. Moreover, we introduce a shuffling technique to weaken the local correlation of noise, which in turn yields an additional denoising performance improvement. We evaluate MASH via extensive experiments on real-world noisy image datasets. We demonstrate on par or better results compared to existing self-supervised denoising methods.
title Masked and Shuffled Blind Spot Denoising for Real-World Images
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2404.09389