Self-Supervised Poisson-Gaussian Denoising
This addresses the problem of denoising microscope images without clean data, but it is incremental as it extends existing blindspot models to a specific noise type.
The paper tackles self-supervised denoising for Poisson-Gaussian noise, common in low-light microscopy, by introducing a hyperparameter-free training strategy and test-time adaptation, achieving validated performance on benchmarks.
We extend the blindspot model for self-supervised denoising to handle Poisson-Gaussian noise and introduce an improved training scheme that avoids hyperparameters and adapts the denoiser to the test data. Self-supervised models for denoising learn to denoise from only noisy data and do not require corresponding clean images, which are difficult or impossible to acquire in some application areas of interest such as low-light microscopy. We introduce a new training strategy to handle Poisson-Gaussian noise which is the standard noise model for microscope images. Our new strategy eliminates hyperparameters from the loss function, which is important in a self-supervised regime where no ground truth data is available to guide hyperparameter tuning. We show how our denoiser can be adapted to the test data to improve performance. Our evaluations on microscope image denoising benchmarks validate our approach.