Image Denoising and the Generative Accumulation of Photons
This work addresses noise removal in fluorescence microscopy images, offering a novel generative approach that is incremental in its application to a specific domain.
The paper tackled image denoising by modeling image formation as a sequential photon accumulation process, resulting in a method that outperforms or matches supervised, self-supervised, and unsupervised baselines on four new fluorescence microscopy datasets.
We present a fresh perspective on shot noise corrupted images and noise removal. By viewing image formation as the sequential accumulation of photons on a detector grid, we show that a network trained to predict where the next photon could arrive is in fact solving the minimum mean square error (MMSE) denoising task. This new perspective allows us to make three contributions: We present a new strategy for self-supervised denoising, We present a new method for sampling from the posterior of possible solutions by iteratively sampling and adding small numbers of photons to the image. We derive a full generative model by starting this process from an empty canvas. We call this approach generative accumulation of photons (GAP). We evaluate our method quantitatively and qualitatively on 4 new fluorescence microscopy datasets, which will be made available to the community. We find that it outperforms supervised, self-supervised and unsupervised baselines or performs on-par.