LightGlueMatcher

Features and matchingclassOpenCV 5.0.0

import { LightGlueMatcher } from '@banou/opencv-wasm'

Use after await initOpenCV(). See the initialization and named imports guide.

ARGUMENTSConstructor or factory

CLASSLightGlueMatcher

RETURN TYPEOwned native handle

Call structure. A void return can still write to destination arguments. The parameter descriptions define inputs, outputs and ownership.

Native object: release it with using or delete(). Factories can return null; check before calling methods. Inherits DescriptorMatcher.

LightGlue feature matcher.

LightGlue is a CNN-based feature matcher, as described in [Lindenberger23] . It takes keypoint locations and descriptors from two images and directly predicts match pairs. Unlike traditional matchers that compute descriptor distances, LightGlue uses attention mechanisms to produce confidence scores for each potential match pair.

The matcher extends DescriptorMatcher and supports the standard match(), knnMatch(), and radiusMatch() interfaces. Context (keypoints and image sizes) must be provided via setPairInfo() before matching.

Upstream declaration ↗

Constructors and members

static create

Creates LightGlueMatcher from a model file path.

create(modelPath: EmbindString, scoreThreshold: number, backend: number, target: number): LightGlueMatcher | null;

4 available overloads

create(modelPath: EmbindString): LightGlueMatcher | null;

create(modelPath: EmbindString, scoreThreshold: number): LightGlueMatcher | null;

create(modelPath: EmbindString, scoreThreshold: number, backend: number): LightGlueMatcher | null;

create(modelPath: EmbindString, scoreThreshold: number, backend: number, target: number): LightGlueMatcher | null;

modelPath: Path to the ONNX model file.
scoreThreshold: Match confidence threshold.
backend: DNN backend
target: DNN target

Returns

The LightGlueMatcher | null result.

Upstream declaration ↗

static createFromMemory

Creates LightGlueMatcher from in-memory model data.

createFromMemory(modelData: ucharVector, scoreThreshold: number, backend: number, target: number): LightGlueMatcher | null;

4 available overloads

createFromMemory(modelData: ucharVector): LightGlueMatcher | null;

createFromMemory(modelData: ucharVector, scoreThreshold: number): LightGlueMatcher | null;

createFromMemory(modelData: ucharVector, scoreThreshold: number, backend: number): LightGlueMatcher | null;

createFromMemory(modelData: ucharVector, scoreThreshold: number, backend: number, target: number): LightGlueMatcher | null;

modelData: Buffer containing the model data.
scoreThreshold: Match confidence threshold.
backend: DNN backend
target: DNN target

Returns

The LightGlueMatcher | null result.

Upstream declaration ↗

setPairInfo

Sets the keypoint and image size context for the next match() call.

This provides the spatial context that LightGlue needs in addition to descriptors.
Must be called before match()/knnMatch()/radiusMatch() unless using automatic context
from in-process ALIKED instances.

setPairInfo(queryKpts: Mat, trainKpts: Mat, queryImageSize: Size, trainImageSize: Size): void;

3 available overloads

setPairInfo(queryKpts: Mat, trainKpts: Mat): void;

setPairInfo(queryKpts: Mat, trainKpts: Mat, queryImageSize: Size): void;

setPairInfo(queryKpts: Mat, trainKpts: Mat, queryImageSize: Size, trainImageSize: Size): void;

queryKpts: Query image keypoints (Nx2 float matrix with x,y coordinates).
trainKpts: Train image keypoints (Nx2 float matrix with x,y coordinates).
queryImageSize: Size of the query image (width, height).
trainImageSize: Size of the train image (width, height).

Upstream declaration ↗

clearPairInfo

Clears stored pair context information.

clearPairInfo(): void;

Upstream declaration ↗

These signatures describe this package. Upstream documentation can mention optional backends that are absent from this build. Check runtime compatibility before choosing a backend or file format.