Joint self-supervised blind denoising and noise estimation
This addresses the challenge of denoising biomedical images where noise is hard to model and clean data are unavailable, offering a practical and efficient solution.
The paper tackles the problem of blind denoising in biomedical images without clean training data by proposing a self-supervised approach where two neural networks jointly predict clean signals and infer noise distributions, significantly outperforming current state-of-the-art methods on six datasets.
We propose a novel self-supervised image blind denoising approach in which two neural networks jointly predict the clean signal and infer the noise distribution. Assuming that the noisy observations are independent conditionally to the signal, the networks can be jointly trained without clean training data. Therefore, our approach is particularly relevant for biomedical image denoising where the noise is difficult to model precisely and clean training data are usually unavailable. Our method significantly outperforms current state-of-the-art self-supervised blind denoising algorithms, on six publicly available biomedical image datasets. We also show empirically with synthetic noisy data that our model captures the noise distribution efficiently. Finally, the described framework is simple, lightweight and computationally efficient, making it useful in practical cases.