Interpretable Unsupervised Diversity Denoising and Artefact Removal
This addresses the problem of ambiguity in image restoration for applications like microscopy where supervised data is scarce, offering an interpretable and unsupervised solution with broad impact.
The paper tackles unsupervised diverse image restoration for denoising and artefact removal, particularly in microscopy, by introducing Hierarchical DivNoising (HDN), which achieves state-of-the-art results on twelve benchmark datasets and successfully removes artefacts on three real microscopy datasets while generating multiple plausible restorations.
Image denoising and artefact removal are complex inverse problems admitting multiple valid solutions. Unsupervised diversity restoration, that is, obtaining a diverse set of possible restorations given a corrupted image, is important for ambiguity removal in many applications such as microscopy where paired data for supervised training are often unobtainable. In real world applications, imaging noise and artefacts are typically hard to model, leading to unsatisfactory performance of existing unsupervised approaches. This work presents an interpretable approach for unsupervised and diverse image restoration. To this end, we introduce a capable architecture called Hierarchical DivNoising (HDN) based on hierarchical Variational Autoencoder. We show that HDN learns an interpretable multi-scale representation of artefacts and we leverage this interpretability to remove imaging artefacts commonly occurring in microscopy data. Our method achieves state-of-the-art results on twelve benchmark image denoising datasets while providing access to a whole distribution of sensibly restored solutions. Additionally, we demonstrate on three real microscopy datasets that HDN removes artefacts without supervision, being the first method capable of doing so while generating multiple plausible restorations all consistent with the given corrupted image.