Struct LightGlueMatcher 

pub struct LightGlueMatcher { /* private fields */ }

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.

Implementations

impl LightGlueMatcher

pub fn create( model_path: impl AsRef<OsStr>, score_threshold: f32, backend: i32, target: i32, ) -> Result<Ptr<LightGlueMatcher>>

Creates LightGlueMatcher from a model file path.

Parameters

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

C++ default parameters

• score_threshold: 0.0f
• backend: 0
• target: 0

pub fn create_def( model_path: impl AsRef<OsStr>, ) -> Result<Ptr<LightGlueMatcher>>

Creates LightGlueMatcher from a model file path.

Parameters

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

Note

This alternative version of LightGlueMatcher::create function uses the following default values for its arguments:

• score_threshold: 0.0f
• backend: 0
• target: 0

pub fn create_from_memory( model_data: &Vector<u8>, score_threshold: f32, backend: i32, target: i32, ) -> Result<Ptr<LightGlueMatcher>>

Creates LightGlueMatcher from in-memory model data.

Parameters

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

C++ default parameters

• score_threshold: 0.0f
• backend: 0
• target: 0

pub fn create_from_memory_def( model_data: &Vector<u8>, ) -> Result<Ptr<LightGlueMatcher>>

Creates LightGlueMatcher from in-memory model data.

Parameters

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

Note

This alternative version of LightGlueMatcher::create_from_memory function uses the following default values for its arguments:

• score_threshold: 0.0f
• backend: 0
• target: 0

Trait Implementations

impl AlgorithmTrait for LightGlueMatcher

fn as_raw_mut_Algorithm(&mut self) -> *mut c_void

fn clear(&mut self) -> Result<()>

Clears the algorithm state

fn read(&mut self, fn_: &impl FileNodeTraitConst) -> Result<()>

Reads algorithm parameters from a file storage

impl AlgorithmTraitConst for LightGlueMatcher

fn as_raw_Algorithm(&self) -> *const c_void

fn write(&self, fs: &mut impl FileStorageTrait) -> Result<()>

Stores algorithm parameters in a file storage

fn write_1(&self, fs: &mut impl FileStorageTrait, name: &str) -> Result<()>

Stores algorithm parameters in a file storage

fn empty(&self) -> Result<bool>

Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read

fn save(&self, filename: impl AsRef<OsStr>) -> Result<()>

Saves the algorithm to a file. In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).

fn get_default_name(&self) -> Result<String>

Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.

impl Boxed for LightGlueMatcher

unsafe fn from_raw( ptr: <LightGlueMatcher as OpenCVFromExtern>::ExternReceive, ) -> Self

Wrap the specified raw pointer

fn into_raw( self, ) -> <LightGlueMatcher as OpenCVTypeExternContainer>::ExternSendMut

Return the underlying raw pointer while consuming this wrapper.

fn as_raw(&self) -> <LightGlueMatcher as OpenCVTypeExternContainer>::ExternSend

Return the underlying raw pointer.

fn as_raw_mut( &mut self, ) -> <LightGlueMatcher as OpenCVTypeExternContainer>::ExternSendMut

Return the underlying mutable raw pointer

impl Debug for LightGlueMatcher

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl DescriptorMatcherTrait for LightGlueMatcher

fn as_raw_mut_DescriptorMatcher(&mut self) -> *mut c_void

fn add(&mut self, descriptors: &impl ToInputArray) -> Result<()>

Adds descriptors to train a CPU(trainDescCollectionis) or GPU(utrainDescCollectionis) descriptor collection.

fn clear(&mut self) -> Result<()>

Clears the train descriptor collections.

fn train(&mut self) -> Result<()>

Trains a descriptor matcher

fn match_( &mut self, query_descriptors: &impl ToInputArray, matches: &mut Vector<DMatch>, masks: &impl ToInputArray, ) -> Result<()>

Finds the best match for each descriptor from a query set.

fn match__def( &mut self, query_descriptors: &impl ToInputArray, matches: &mut Vector<DMatch>, ) -> Result<()>

Finds the best match for each descriptor from a query set.

fn knn_match( &mut self, query_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, k: i32, masks: &impl ToInputArray, compact_result: bool, ) -> Result<()>

Finds the k best matches for each descriptor from a query set.

fn knn_match_def( &mut self, query_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, k: i32, ) -> Result<()>

Finds the k best matches for each descriptor from a query set.

fn radius_match( &mut self, query_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, max_distance: f32, masks: &impl ToInputArray, compact_result: bool, ) -> Result<()>

For each query descriptor, finds the training descriptors not farther than the specified distance.

fn radius_match_def( &mut self, query_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, max_distance: f32, ) -> Result<()>

For each query descriptor, finds the training descriptors not farther than the specified distance.

fn read(&mut self, file_name: impl AsRef<OsStr>) -> Result<()>

fn read_from_node(&mut self, unnamed: &impl FileNodeTraitConst) -> Result<()>

impl DescriptorMatcherTraitConst for LightGlueMatcher

fn as_raw_DescriptorMatcher(&self) -> *const c_void

fn get_train_descriptors(&self) -> Result<Vector<Mat>>

Returns a constant link to the train descriptor collection trainDescCollection .

fn empty(&self) -> Result<bool>

Returns true if there are no train descriptors in the both collections.

fn is_mask_supported(&self) -> Result<bool>

Returns true if the descriptor matcher supports masking permissible matches.

fn train_match( &self, query_descriptors: &impl ToInputArray, train_descriptors: &impl ToInputArray, matches: &mut Vector<DMatch>, mask: &impl ToInputArray, ) -> Result<()>

Finds the best match for each descriptor from a query set.

fn train_match_def( &self, query_descriptors: &impl ToInputArray, train_descriptors: &impl ToInputArray, matches: &mut Vector<DMatch>, ) -> Result<()>

Finds the best match for each descriptor from a query set.

fn knn_train_match( &self, query_descriptors: &impl ToInputArray, train_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, k: i32, mask: &impl ToInputArray, compact_result: bool, ) -> Result<()>

Finds the k best matches for each descriptor from a query set.

fn knn_train_match_def( &self, query_descriptors: &impl ToInputArray, train_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, k: i32, ) -> Result<()>

Finds the k best matches for each descriptor from a query set.

fn radius_train_match( &self, query_descriptors: &impl ToInputArray, train_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, max_distance: f32, mask: &impl ToInputArray, compact_result: bool, ) -> Result<()>

For each query descriptor, finds the training descriptors not farther than the specified distance.

fn radius_train_match_def( &self, query_descriptors: &impl ToInputArray, train_descriptors: &impl ToInputArray, matches: &mut Vector<Vector<DMatch>>, max_distance: f32, ) -> Result<()>

For each query descriptor, finds the training descriptors not farther than the specified distance.

fn write(&self, file_name: impl AsRef<OsStr>) -> Result<()>

fn write_to_storage(&self, unnamed: &mut impl FileStorageTrait) -> Result<()>

fn clone(&self, empty_train_data: bool) -> Result<Ptr<DescriptorMatcher>>

Clones the matcher.

fn clone_def(&self) -> Result<Ptr<DescriptorMatcher>>

Clones the matcher.

fn write_to_storage_with_name( &self, fs: &mut impl FileStorageTrait, name: &str, ) -> Result<()>

impl Drop for LightGlueMatcher

fn drop(&mut self)

Executes the destructor for this type.

fn pin_drop(self: Pin<&mut Self>)

🔬This is a nightly-only experimental API. (pin_ergonomics)

Execute the destructor for this type, but different to Drop::drop, it requires self to be pinned.

impl From<LightGlueMatcher> for Algorithm

fn from(s: LightGlueMatcher) -> Self

Converts to this type from the input type.

impl From<LightGlueMatcher> for DescriptorMatcher

fn from(s: LightGlueMatcher) -> Self

Converts to this type from the input type.

impl LightGlueMatcherTrait for LightGlueMatcher

fn as_raw_mut_LightGlueMatcher(&mut self) -> *mut c_void

fn set_pair_info( &mut self, query_kpts: &impl ToInputArray, train_kpts: &impl ToInputArray, query_image_size: Size, train_image_size: Size, ) -> Result<()>

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

fn set_pair_info_def( &mut self, query_kpts: &impl ToInputArray, train_kpts: &impl ToInputArray, ) -> Result<()>

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

fn clear_pair_info(&mut self) -> Result<()>

Clears stored pair context information.

impl LightGlueMatcherTraitConst for LightGlueMatcher

fn as_raw_LightGlueMatcher(&self) -> *const c_void

impl Send for LightGlueMatcher

impl TryFrom<DescriptorMatcher> for LightGlueMatcher

type Error = Error

The type returned in the event of a conversion error.

fn try_from(s: DescriptorMatcher) -> Result<Self>

Performs the conversion.