Activity: Academic and Industrial events › Guest lecture or Invited talk
Description
Early approaches to learning-based denoising were supervised, i.e., they required pairs of clean and noisy data for training. While theoretically applicable to many types of data and noise, in practice, the requirement for pairs greatly limited their applicability.
Later, the community developed self-supervised methods, which only required unpaired noisy data for training. Such methods are based on making assumptions about the nature of the noise, which are often (but not always) correct.
Finally, unsupervised methods were introduced, which train deep generative models for the data and noise. Like self-supervised methods, they can be trained using only noisy data. Instead of outputting a single denoised image, these methods allow us to account for the uncertainty in the denoising process by producing samples of possible solutions.
The talk will provide an overview of these three types of methods, as well as their strengths and limitations.