Skip to yearly menu bar Skip to main content


Poster

Masked and Shuffled Blind Spot Denoising for Real-World Images

Hamadi Chihaoui · Paolo Favaro

Arch 4A-E Poster #279
[ ] [ Paper PDF ]
[ Slides [ Poster
Wed 19 Jun 10:30 a.m. PDT — noon PDT

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.

Chat is not available.