Skip to content

Algorithms#

Work in progress

These pages are still under construction and we expect a lot more details descriptions of each algorithm in the near future.

In these pages, you will find explanations and illustrations of how the various algorithms used in CAREamics work. These algorithms are divided into different sections and a few keywords help you to understand the main characteristics of each algorithm.

Keywords#

  • no ground-truth: The algorithm trains without clean images.
  • single image: The algorithm can train on a single image.
  • pairs of noisy images: The algorithm requires pairs of noisy images.
  • ground-truth: The algorithm requires pairs of clean and noisy images.

Self-supervised restoration#

Noise2Void

A self-supervised denoising algorithm based on a pixel masking scheme.

no ground-truth single image
N2V2

A variant of Noise2Void capable of removing checkboard artefacts.

no ground-truth single image
StructN2V

A variant of Noise2Void that uses an enhanced mask to remove structured noise.

no ground-truth single image
Noise2Noise

A supervised methods that can denoise images without corresponding clean data.

no ground-truth pairs of noisy images

Supervised restoration#

CARE

The original supervised method to restore microscopy images.

ground-truth