PSFGenerator

class deepinv.physics.generator.PSFGenerator(psf_size=(31, 31), num_channels=1, **kwargs)

Bases: PhysicsGenerator

Base class for generating Point Spread Functions (PSFs).

Parameters:

• psf_size (tuple) – the shape of the generated PSF in 2D (kernel_size, kernel_size). If an int is given, it will be used for both dimensions.

• num_channels (int) – number of images channels. Defaults to 1.

Examples using PSFGenerator:

Imaging inverse problems with adversarial networks

Imaging inverse problems with adversarial networks

5 minute quickstart tutorial

5 minute quickstart tutorial

Inference and fine-tune a foundation model

Inference and fine-tune a foundation model

Tour of blur operators

Tour of blur operators

3D diffraction PSF

3D diffraction PSF

Solving blind inverse problems / estimating physics parameters

Solving blind inverse problems / estimating physics parameters