MaskFromBoundingBox<T>

Models & Types · AiDotNet.Diffusion.MaskUtilities

Generates a mask from one or more bounding box regions.

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

For Beginners

If you have a bounding box around an object (like from an object detector), this utility converts that box into a mask you can use for inpainting or editing that specific region.

How It Works

Creates a binary mask where pixels inside any of the specified bounding boxes are masked (1) and all other pixels are unmasked (0). Useful for region-based inpainting from object detection results.

When used as an IDataTransformer, the Transform method takes an image tensor, uses its dimensions for height/width, and generates a mask from the bounding boxes configured in the constructor.

Constructors

Constructor Summary
MaskFromBoundingBox(ValueTuple<int, int, int, int>[] boxes) Initializes a new instance of the MaskFromBoundingBox class.

Properties

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

Methods

Method Summary
Tensor<T> FitTransform(Tensor<T> data)
Tensor<T> Generate(int height, int width, ValueTuple<int, int, int, int>[] boxes) Generates a mask covering the specified bounding boxes.
Tensor<T> InverseTransform(Tensor<T> data)
Tensor<T> Transform(Tensor<T> data) Generates a bounding box mask using the input tensor’s dimensions and the boxes configured in the constructor.
string[] GetFeatureNamesOut(string[] inputFeatureNames)
void Fit(Tensor<T> data)