Masked and Shuffled Blind Spot Denoising for Real-World Images

TL;DR

The paper presents MASH, a novel self-supervised image denoising method that effectively handles correlated noise in real-world images by combining masking and shuffling techniques, outperforming existing methods.

Contribution

Introduction of MASH, a new blind spot denoising approach that uses masking and shuffling to improve denoising of correlated noise in real images.

Findings

Achieves comparable or superior results to existing methods.

Effectively reduces noise correlation through shuffling.

Demonstrates robustness on real-world noisy datasets.

Abstract

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.