Upscale

class deeptrack.features.Upscale(feature: Feature, factor: int | Tuple[int, int, int] = 1, **kwargs: Dict[str, Any])

Bases: Feature

Perform the simulation at a higher resolution.

This feature scales up the resolution of the input pipeline by a specified factor, performs computations at the higher resolution, and then downsamples the result back to the original size. This is useful for simulating effects at a finer resolution while preserving compatibility with lower-resolution pipelines.

It redefines the sizes of internal units to scale up the simulation. The resulting image is then downscaled back to the original size.

Parameters

featureFeature

The pipeline or feature to resolve at a higher resolution.

factorint or Tuple[int, int, int], optional

The factor by which to upscale the simulation. If a single integer is provided, it is applied uniformly across all axes. If a tuple of three integers is provided, each axis is scaled individually. Defaults to 1.

**kwargsDict[str, Any]

Additional keyword arguments passed to the parent Feature class.

Attributes

__distributed__bool

Indicates whether this feature distributes computation across inputs. Always False for Upscale.

Methods

get(image, factor, **kwargs)

Scales up the pipeline, performs computations, and scales down result.

Example

>>> import deeptrack as dt
>>> optics = dt.Fluorescence()
>>> particle = dt.Sphere()
>>> pipeline = optics(particle)
>>> upscaled_pipeline = dt.Upscale(pipeline, factor=4)

Methods Summary

get(image, factor, **kwargs)

Scale up resolution of feature pipeline and scale down result.

Methods Documentation

get(image: ndarray, factor: int | Tuple[int, int, int], **kwargs: Dict[str, Any]) → ndarray

Scale up resolution of feature pipeline and scale down result.

Parameters

imagenp.ndarray

The input image to process.

factorint or Tuple[int, int, int]

The factor by which to upscale the simulation. If a single integer is provided, it is applied uniformly across all axes. If a tuple of three integers is provided, each axis is scaled individually.

**kwargsDict[str, Any]

Additional keyword arguments passed to the feature.

Returns

np.ndarray

The processed image at the original resolution.

Raises

ValueError

If the input factor is not a valid integer or tuple of integers.