Masked and Shuffled Blind Spot Denoising for Real-World Images
This addresses denoising for real-world images where noise is correlated, offering an incremental improvement over prior self-supervised techniques.
The paper tackles single image denoising for real-world images with correlated noise by introducing MASH, a method based on blind spot denoising with masking and shuffling, and shows it achieves on par or better results than existing self-supervised methods.
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.