MaskBlur<T>

Models & Types · AiDotNet.Diffusion.MaskUtilities

Applies Gaussian blur to a mask for smooth transitions.

Implements: IDataTransformer<T, Tensor<T>, Tensor<T>>

For Beginners

This blurs a mask like blurring a photo — sharp edges become soft gradients. It’s similar to feathering but affects the whole mask, not just edges. Use this when you want an overall softer mask with gradual transitions everywhere.

How It Works

Blurs the entire mask using a Gaussian kernel, softening all edges and transitions. Unlike feathering which targets edges specifically, blur affects the entire mask uniformly. Useful for creating soft masks from hard binary masks.

Constructors

Constructor Summary
MaskBlur(double sigma) Initializes a new instance of the MaskBlur class.

Properties

Property Summary
bool IsFitted { get; }
bool SupportsInverseTransform { get; }
int[] ColumnIndices { get; }

Methods

Method Summary
Tensor<T> Apply(Tensor<T> mask) Applies Gaussian blur to a mask tensor.
Tensor<T> FitTransform(Tensor<T> data)
Tensor<T> InverseTransform(Tensor<T> data)
Tensor<T> Transform(Tensor<T> data)
string[] GetFeatureNamesOut(string[] inputFeatureNames)
void Fit(Tensor<T> data)