Crate spatialrust

Expand description

SpatialRust meta crate.

Re-exports the stable public API surface. Application code should depend on this crate unless it needs direct access to a specific sub-crate.

Re-exports§

pub use spatialrust_core as core;
pub use spatialrust_features as features;
pub use spatialrust_filtering as filtering;
pub use spatialrust_gpu as gpu;
pub use spatialrust_io as io;
pub use spatialrust_math as math;
pub use spatialrust_metrics as metrics;
pub use spatialrust_pipeline as pipeline;
pub use spatialrust_registration as registration;
pub use spatialrust_search as search;
pub use spatialrust_segmentation as segmentation;
pub use spatialrust_transform as transform;
pub use spatialrust_voxelize as voxelize;
pub use spatialrust_ai as ai;
pub use spatialrust_arrow as arrow;
pub use spatialrust_camera as camera;
pub use spatialrust_distribute as distribute;
pub use spatialrust_episode as episode;
pub use spatialrust_image as image;
pub use spatialrust_image_io as image_io;
pub use spatialrust_interchange as interchange;
pub use spatialrust_lod as lod;
pub use spatialrust_mapping as mapping;
pub use spatialrust_platform as platform;
pub use spatialrust_records as records;
pub use spatialrust_render_wgpu as render_wgpu;
pub use spatialrust_ros2 as ros2;
pub use spatialrust_runtime as runtime;
pub use spatialrust_scene as scene;
pub use spatialrust_semantic as semantic;
pub use spatialrust_sync as sync;
pub use spatialrust_tensor as tensor;
pub use spatialrust_viewer as viewer;
pub use spatialrust_vision as vision;
pub use spatialrust_viz as viz;
pub use spatialrust_web as web;

Structs§

Aabb: Axis-aligned bounding box used by CropBox.
AbsolutePose: Object-to-camera pose X_cam = R X_obj + t used by absolute orientation (PnP).
AdaptiveBackgroundModel: Stateful single-Gaussian grayscale background model.
AffineTransform: A source-to-destination 2D affine transform.
AoSoAAttributeChunk: Owned interleaved positions and optional capability attributes for one chunk.
AoSoAAttributeLayout: Explicit interleaved field layout for an AoSoAAttributeChunk.
AoSoAXyzChunk: Interleaved XYZ layout for one SpatialTensorChunk (3 * point_count floats).
AreaResizeU8Plan: Reusable weighted-span plan for packed u8 area resize.
BackgroundModelOptions: Adaptive Gaussian background-model controls.
BackgroundUpdate: Output of one background-model update.
BilinearResizeU8Plan: Reusable source coordinates and fixed-point coefficients for u8 bilinear resize.
BinaryMask: Validated binary mask (0 background, 1 foreground).
BoundaryConfig: Configuration for BoundaryDetector.
BoundaryDetector: Tangent-plane boundary point detector. The input cloud must carry normals.
BoundaryResult: Result of boundary detection.
BoundingBox2: Axis-aligned bounding box using half-open (min, max) coordinates.
BrownConrady: Brown–Conrady radial and tangential lens-distortion coefficients.
BruteForceIndex: Reference index using brute-force search for correctness tests.
CameraIntrinsics: Pinhole camera intrinsic parameters and image dimensions.
CameraMatrix3: Calibrated pinhole intrinsic matrix and its analytic inverse.
CannyOptions: Validated Canny thresholds and gradient settings.
CannyResult: Edge map and numerical stages produced by Canny.
CannyWorkspace: Reusable caller-owned storage for the allocation-light Canny path.
CauchyKernel: Cauchy robust kernel.
ChunkMapSource: Bounded source adapter for chunk-local crop and affine transform operations.
CloudDistances: A bundle of directed and symmetric cloud-to-cloud distance statistics.
ComponentStats: Per-component statistics.
ConfidenceMap: Dense confidence values constrained to [0, 1].
ConnectedComponents: Connected-component labeling output.
Contour: One closed polygonal contour on pixel-grid corner coordinates.
CopcBounds: Axis-aligned bounds for COPC spatial queries.
CopcFileInfo: Metadata exposed from a COPC header without loading point data.
CopcQuery: Spatial query parameters for partial COPC reads.
CopcWriterParams
CornerSelectionOptions: Shared response thresholding and spatial suppression options.
Cov3: 3x3 symmetric covariance matrix.
CovarianceAccumulator3: Accumulates mean and covariance for 3D points.
CpuDevice: Default CPU device.
CpuRuntime: Host runtime for single-threaded and parallel CPU algorithms.
CropBox: Keeps (or, when invert is set, drops) points inside an axis-aligned box.
CylinderModel: Cylinder model: all surface points are radius from the axis line.
DatasetManifest: JSON manifest containing the files associated with one dataset operation.
DbscanConfig: Configuration for DBSCAN density-based clustering.
DbscanResult: Result of DBSCAN clustering.
DbscanSegmenter: DBSCAN density-based segmenter.
DecodeLimits: Strict application-level resource limits for one decode operation.
DecodeOptions: Options controlling one decode operation.
DecodedImage: One decoded image with owned typed pixels and source metadata.
DecodedMetadata: Metadata describing encoded pixels and orientation handling.
DenseFlowOptions: Integer block-matching controls for dense grayscale optical flow.
DepthConversionOptions: Controls conversion from stored depth values to metric camera coordinates.
DepthMap: Metric or relative dense depth map. Non-positive and non-finite values are invalid.
DescriptorBuffer: Row-major descriptor matrix with a fixed width and explicit scalar kind.
Detection: One scored detection used by class-aware post-processing.
DistanceTransformWorkspace: Reusable host scratch storage for the unit-spacing exact distance transform.
EncodeOptions: Options controlling encoded output.
Essential3: A calibrated two-view epipolar constraint matrix.
EuclideanClusterConfig: Configuration for Euclidean clustering.
EuclideanClusterExtractor: Euclidean region-growing cluster extractor.
EuclideanClusterResult: Result of Euclidean clustering.
ExecutionOutput: Output value paired with the receipt for its execution.
ExecutionReceipt: Account of one algorithm execution.
ExposureFusionOptions: Well-exposedness fusion controls.
FarthestPointSampling: Farthest Point Sampling downsampler.
FarthestPointSamplingConfig: Configuration for FarthestPointSampling.
FastOptions: FAST detector configuration for the standard 9-of-16 radius-three circle.
FeatureMatch: One descriptor correspondence from a query feature to a train feature.
FeatureSet2: Keypoints paired one-to-one with descriptor rows.
FileReceipt: Size and SHA-256 receipt for one local file or URI source.
FlowField: Dense (dx, dy) optical-flow field in pixel units.
FpfhRansacConfig: Configuration for FpfhRansacRegistration.
FpfhRansacRegistration: FPFH + RANSAC global registration.
FrameId: Coordinate frame identifier.
Fundamental3: An uncalibrated two-view epipolar constraint matrix.
GaussianBlurU8Workspace: Reusable scratch storage and fixed-point kernel cache for gaussian_blur_u8_into.
GeometricEstimate: A geometric model paired with one inlier decision and residual per input row.
GicpConfig: Configuration for Generalized ICP (plane-to-plane).
GicpRegistration: Generalized ICP registration.
GpuEuclideanClusterExtractor: GPU-grid-backed Euclidean cluster extractor.
GpuNormalEstimator: GPU-accelerated normal estimator.
GpuRansacPlaneSegmenter: GPU-accelerated RANSAC plane segmenter.
GridSelectionOptions: Controls deterministic spatial distribution of candidate keypoints.
GroundConfig: Configuration for GroundSegmenter.
GroundSegmentation: Result of ground segmentation.
GroundSegmenter: Grid-based ground segmenter.
HarrisOptions: Harris detector configuration.
Homography3: A pixel-to-pixel planar projective transform.
HttpByteSource: Random-access COPC byte source backed by HTTP range requests.
HuberKernel: Huber robust kernel.
IcpConfig: Configuration for point-to-point ICP.
IcpRegistration: Point-to-point ICP registration.
Image: An owning, densely packed, interleaved image.
ImageMetadata: Lightweight semantic metadata carried by images and borrowed views.
ImageRegion: A checked rectangular image region.
ImageView: A read-only, zero-copy image view with an explicit row stride.
ImageViewMut: A mutable, zero-copy interleaved image view with an explicit row stride.
IntegralImage: Summed-area table with a zero top row and left column.
Isometry3: Proper rigid transform: rotation + translation without scale/shear.
IssKeypointConfig: Configuration for IssKeypointDetector.
IssKeypointDetector: Intrinsic Shape Signatures keypoint detector.
IssKeypointResult: Result of ISS keypoint detection.
KdTree: Cache-friendly KD-tree for 3D point clouds.
KdTreeNeighborhood: KD-tree backed neighborhood provider.
Kernel1D: Validated one-dimensional correlation kernel.
Kernel2D: Validated two-dimensional correlation kernel.
Keypoint2: One scale-space image keypoint in pixel coordinates.
LabelImage: Connected-component label image (0 is background).
LetterboxTransform: Mapping between a source image and its letterboxed output.
LucasKanadeOptions: Configuration for sparse Lucas–Kanade tracking.
ManifestValidation: Summary returned after re-hashing every local manifest entry.
MaskRle: Alternating zero/one run lengths, always beginning with a zero run.
Mat3: 3x3 matrix stored in row-major order.
Mat4: 4x4 matrix stored in row-major order.
MatchOptions: Filtering applied to brute-force descriptor correspondences.
MemoryVideoSource: Deterministic in-memory source used for adapter conformance and replay.
MlsConfig: Configuration for MlsSmoothing.
MlsSmoothing: Moving Least Squares smoothing filter.
MonocularOdometryEstimate: Scale-ambiguous monocular odometry result.
MultiObjectTracker: Deterministic same-class greedy IoU multi-object tracker.
MultiObjectTrackerOptions: IoU tracker controls.
MultiPlaneConfig: Configuration for MultiPlaneSegmenter.
MultiPlaneSegmentation: Result of multi-plane segmentation.
MultiPlaneSegmenter: Sequential RANSAC multi-plane segmenter.
MvpIcpConfig: Configuration for optional ICP in the MVP pipeline.
MvpPipeline: Builder-style MVP pipeline runner.
MvpPipelineConfig: Full configuration for the MVP pipeline.
MvpPipelineReceipt: Execution receipt for the stages of one MVP pipeline run.
MvpPipelineResult: Output of a completed MVP pipeline run.
NdtConfig: Configuration for NDT (Normal Distributions Transform) registration.
NdtRegistration: NDT registration (point-to-distribution).
NearestResizeU8Plan: Reusable source-coordinate plan for packed u8 nearest-neighbor resize.
Neighbor: One neighbor search result.
NeighborGraph: A directed neighborhood graph over a point cloud.
NormalEstimationConfig: Configuration for covariance-based normal estimation.
NormalEstimationResult: Result metadata for normal estimation.
NormalEstimator: Covariance-based normal estimator.
NormalOrientationConfig: Configuration for orient_normals_consistent.
Obb: Oriented bounding box recovered from the principal axes of a cloud.
ObjectImageCorrespondence: One ordered object-to-image correspondence for absolute pose estimation.
ObjectTrack: One deterministic detection track.
OccupancyGrid: A dense 3D grid in row-major (z, y, x) order.
OrbOptions: Multi-scale ORB detector and descriptor configuration.
Padding: Padding applied around an image.
Panorama: Pairwise panorama and its integer world-coordinate origin.
PanoramaOptions: Bounded pairwise panorama settings.
PassThrough: Keeps (or drops) points whose value in a named field falls within a range.
PerspectiveTransform: A source-to-destination projective 2D transform.
PinholeCamera: A pinhole camera with optional Brown–Conrady lens distortion.
PlanarImage: An owning, densely packed planar image.
PlanarImageView: A read-only, zero-copy planar image view with explicit strides.
PlaneModel: Plane model in Hessian form: normal · p + d = 0 with unit normal.
PointCloud: Schema-aware columnar point cloud stored on a device.
PointCloudBuilder: Builds point clouds field-by-field.
PointCorrespondence2: One ordered pixel correspondence from a source image to a target image.
PointField: One column in a point cloud schema.
PointMap: Dense per-pixel XYZ point map. Non-finite triples represent invalid points.
PointSchema: Schema describing the columns of a point cloud.
PointToPlaneIcp: Point-to-plane ICP registration.
PointToPlaneIcpConfig: Configuration for point-to-plane ICP.
Pose3: Pose with optional translation covariance.
PositionReduction: Deterministic global position reduction over a bounded source.
PrimitiveSegmentation: Result of fitting a primitive, partitioning the cloud into inliers/outliers.
Quat: Unit quaternion representing a 3D rotation.
RadiusOutlierConfig: Configuration for RadiusOutlierRemoval.
RadiusOutlierRemoval: Radius Outlier Removal (ROR).
RangeImage: A dense range image in row-major order (row * width + col).
RangeImageConfig: Configuration for range_image.
RansacCylinderSegmenter: RANSAC cylinder segmenter. The input cloud must carry normals.
RansacPlaneConfig: Configuration for RANSAC plane segmentation.
RansacPlaneSegmentation: Result of RANSAC plane segmentation.
RansacPlaneSegmenter: RANSAC-based dominant plane segmenter.
RansacPrimitiveConfig: Shared RANSAC controls for primitive fitting.
RansacSphereSegmenter: RANSAC sphere segmenter.
RectMorphologyWorkspace: Reusable scratch storage for packed grayscale rectangular morphology.
RegionGrowingConfig: Configuration for normal-based region growing segmentation.
RegionGrowingResult: Result of region growing segmentation.
RegionGrowingSegmenter: Normal-based region growing segmenter.
RegistrationResult: Result of a registration run.
RelativePose: Target-camera pose expressed in the source-camera coordinate frame.
RelativePoseEstimate: Essential-matrix pose disambiguation and per-correspondence triangulation.
RgbdOdometryEstimate: Metric previous-camera to current-camera odometry result.
RgbdOdometryOptions: Depth filtering and PnP RANSAC controls for metric RGB-D odometry.
RobustEstimationOptions: Deterministic robust-model sampling and inlier classification settings.
RobustTrackOptions: Forward/backward consistency settings layered over pyramidal LK.
RobustTracks: One target coordinate, validity decision, and round-trip error per source point.
ScoredIndex: Index and possibly updated score returned by Soft-NMS.
ShiTomasiOptions: Shi–Tomasi minimum-eigenvalue detector configuration.
SpatialMetadata: Spatial metadata attached to point clouds and maps.
SpatialTensor: Borrowed chunked view over a PointCloud.
SpatialTensorChunk: One contiguous index range within a SpatialTensor chunk iteration.
SphereModel: Sphere model: all surface points are radius from center.
StandardSchemas: Standard schemas used by typed views and IO adapters.
StatisticalOutlierConfig: Configuration for StatisticalOutlierRemoval.
StatisticalOutlierRemoval: Statistical Outlier Removal (SOR).
StereoBmOptions: Block-matching stereo options.
StereoRectifyMaps: Remap grids produced by stereo rectification for explicit warp::remap.
StereoRig: Calibrated two-camera stereo geometry.
StoragePreflight: Result of a fail-closed output-root free-space check.
StorageRoots: Optional roots used to resolve logical input and output paths.
StreamingVoxelConfig: Configuration for deterministic, spill-backed global voxel centroids.
StreamingVoxelSource: Bounded source of globally aggregated voxel centroids.
StructuringElement: A validated binary neighborhood mask and anchor.
SymmetricEigen3: Result of a symmetric 3x3 eigendecomposition.
Timestamp: Timestamp in nanoseconds since an arbitrary epoch.
TrackedPoints: Result of sparse point tracking between two frames.
TransferStats: Byte accounting for explicit execution transfers.
Transform3: Rigid transform represented as a 4x4 matrix.
TransformAabb: Axis-aligned bounding box.
TriangulatedPoint: One two-view triangulation with cheirality and reprojection diagnostics.
TukeyKernel: Tukey biweight robust kernel.
Vec2: 2D vector.
Vec3: 3D vector.
Vec4: 4D vector.
VideoFrame: Timestamped owned video frame.
VoxelGridConfig: Configuration for voxelize.
VoxelGridDownsample: Voxel-grid downsampling filter.
VoxelGridDownsampleConfig: Configuration for voxel-grid downsampling.

Enums§

AdaptiveThresholdMethod: Adaptive neighborhood statistic.
AlphaMode: Alpha-channel interpretation.
AttributeAggregation: Attribute aggregation policy for non-position fields.
BorderMode: Out-of-bounds sampling behavior for CPU image operations.
CameraError: Camera model errors.
ChunkMapOperation: Per-chunk operation that preserves the input schema.
ColorRange: Numeric range convention associated with image channels.
ColorSpace: Semantic interpretation of image channels.
Connectivity: Pixel connectivity used by binary-mask algorithms.
DType: Supported scalar dtypes for point fields.
DecodedPixels: Owned typed pixels produced by a decoder or accepted by an encoder.
DescriptorKind: Scalar representation used by a descriptor matrix.
DeviceKind: Device kind supported by SpatialRust execution.
ExecutionPolicy: Execution policy for spatial algorithms.
FieldSemantic: Semantic meaning of a point field.
ImageError: Errors raised while constructing or indexing images.
ImageFileFormat: File formats recognized by the stable SpatialRust image-IO boundary.
ImageIoError: Errors produced by bounded image IO.
ImageLayout: Physical channel arrangement in CPU storage.
Interpolation: Sampling filter used by image resampling and geometric warps.
IoError: IO-specific error type for SpatialRust.
LasWriteFormat: Output encoding for LAS writers.
LeastSquaresResult: Result of a small dense linear solve.
MorphologyOperation: Composite morphology operation.
MorphologyShape: Built-in structuring-element geometry.
MvpRegistrationMethod: Registration backend used by the MVP pipeline’s optional alignment step.
OrbScoreType: Response used to rank ORB keypoints.
Orientation: Exif image orientation in encoded-pixel coordinates.
PcdWriteFormat: Output encoding for PCD writers.
PlyWriteFormat: Output encoding for PLY writers.
PointBuffer: Typed column buffer for one point field.
PointCloudFileFormat: Supported point cloud file formats detected from file extensions.
ReceiptRole: Logical role of a file in a dataset operation.
RgbdError: Errors from RGB-D conversion.
RleOrder: Linearization order used by run-length encoded masks.
SoftNmsMethod: Soft-NMS score-decay strategy.
SourceColorType: Encoded sample/channel type before conversion into SpatialRust storage.
SpatialError: Core error type for SpatialRust.
ThresholdType: Point-wise threshold transformation.
TrackState: Track lifecycle state.
TransferDirection: Direction of an explicit data transfer between host and device memory.
UpAxis: Which axis points “up” (its minimum defines local ground height).
VisionError: Errors raised by image and vision algorithms.
VoxelAggregationMode: Voxel aggregation strategy.
VoxelFill: How a voxel’s value is filled from the points that fall in it.

Constants§

DATASET_MANIFEST_VERSION: Current JSON schema version for DatasetManifest.
DEFAULT_GPU_MIN_POINTS_EUCLIDEAN: Minimum point count before GPU Euclidean clustering is selected under Auto.
DEFAULT_GPU_MIN_POINTS_PLANE: Minimum point count before GPU RANSAC plane scoring is selected under Auto.
DEFAULT_MIN_OUTPUT_FREE_BYTES: Initial v1.3 minimum free-space floor for an external output root.
DEFAULT_SPATIAL_TENSOR_CHUNK_SIZE: Default chunk size for PointCloud::spatial_tensor_chunks.
FPFH_DESCRIPTOR_LEN: Length of an FPFH descriptor (33: three 11-bin angular histograms).
INVALID_DISPARITY: Invalid disparity sentinel written by stereo_block_match.
PARALLEL_CHUNK_QUERY_MIN_POINTS: Minimum point count before threaded chunk dispatch is used.
PARALLEL_STAGING_MIN_POINTS: Minimum point count before multi-threaded index staging is used.

Traits§

ChunkedNearestNeighborIndex: k-NN search over contiguous query index ranges.
ChunkedRadiusSearchIndex: Radius search over contiguous query index ranges.
Device: Minimal device abstraction defined in core and extended by spatialrust-gpu.
FeatureEstimator: Computes point-wise features from an input point cloud.
HasIntensity: Capability trait for point clouds with intensity values.
HasNormals3: Capability trait for point clouds with surface normals.
HasPositions3: Capability trait for point clouds with 3D positions.
NearestNeighborIndex: Exact nearest neighbor queries.
NeighborhoodProvider: Neighborhood query abstraction for feature estimation.
PixelComponent: Scalar component supported by generic CPU image kernels.
PointCloudFilter: Point cloud filter interface.
PointCloudRegistration: Common trait for point cloud registration algorithms.
PointCloudSegmenter: Common trait for point cloud segmentation algorithms.
RadiusSearchIndex: Radius search queries.
Real: Floating-point scalar used by spatial algorithms.
RobustKernel: Robust loss kernel used by registration and estimation algorithms.
Scalar: Numeric types supported by SpatialRust math primitives.
SpatialAlgorithm: Common trait implemented by spatial algorithms.
SpatialIndex: Common spatial index operations.
SpatialRuntime: Runtime boundary for executing spatial algorithms on one backend.
TransformPoint: Trait for types that can transform 3D points.
VideoFrameSource: Pull-based video source implemented by optional codec/camera adapters.

Functions§

adaptive_threshold: Applies adaptive binary thresholding to an 8-bit grayscale image.
apply_transform: Applies a 4×4 affine transform to a cloud’s positions (and normals, if present — normals are rotated by the linear part and renormalized).
approx_eq: Returns whether two values are approximately equal.
approx_eq_f64: Returns whether two values are approximately equal.
approximate_polygon: Simplifies a closed contour with Ramer–Douglas–Peucker approximation.
batched_nms: Class-aware greedy NMS over detection records.
bilateral_filter: Applies an edge-preserving bilateral filter.
bounding_box: Axis-aligned bounding box of a cloud.
box_blur: Applies a normalized rectangular box filter.
brute_force_knn: Finds up to k nearest neighbors by brute force.
brute_force_radius: Finds all neighbors within radius by brute force.
build_gaussian_pyramid: Builds a packed Gaussian pyramid including the input as level zero.
canny: Finds edges in a single-channel u8 image.
canny_into: Finds edges into caller-owned output using reusable CPU workspace.
canny_with_intermediates: Runs Canny and retains gradient, magnitude, and suppression stages.
centroid: Centroid (mean position) of a cloud.
chamfer_distance: Symmetric Chamfer distance between two clouds (sum of mean squared NN distances in both directions). Lower is better; zero for identical clouds.
clahe: Applies contrast-limited adaptive histogram equalization to grayscale u8.
cloud_distances: Computes directed NN distance statistics between a and b in both directions with a single KD-tree per side.
connected_components: Labels foreground components and computes bounding boxes and centroids.
connected_components_u8: Labels connected non-zero pixels from packed u8 mask storage.
convolve2d: Applies true convolution by reversing the supplied kernel around its anchor.
copc_level_for_resolution: Computes the shallowest octree level whose spacing is at most resolution.
crop: Copies a checked rectangular region into a packed image.
decode_bytes: Decodes an image from an encoded byte slice.
decode_path: Opens and decodes one image path using content-based format detection.
decode_reader: Reads a bounded encoded stream and decodes it.
decode_rle: Decodes a run-length mask and validates its total length.
dense_flow_block_match: Computes a dense integer flow field with deterministic local block matching.
depth_map_to_point_cloud: Unprojects a depth map with a calibrated camera into an XYZ point cloud.
depth_tensor_to_depth_map: Converts a host depth tensor into a DepthMap.
depth_to_point_cloud: Converts an aligned depth image into an XYZ point cloud.
depth_to_xyz_dense: Converts depth into a dense H×W×3 XYZ buffer (row-major interleaved).
depth_to_xyz_dense_into: Fills a caller-provided dense H×W×3 XYZ buffer (length must be H*W*3).
detect_and_describe_orb: Detects oriented multi-scale keypoints and computes 256-bit rotated BRIEF descriptors.
detect_fast: Detects FAST-9/16 corners in scan order, matching OpenCV’s radius-three ROI.
detect_harris: Detects Harris corners and returns strongest-first keypoints.
detect_point_cloud_format: Detects a point cloud format from a file path extension.
detect_shi_tomasi: Detects Shi–Tomasi corners and returns strongest-first keypoints.
detection_tensor_to_detections: Decodes axis-aligned detections from an [N,6] tensor of x0,y0,x1,y1,score,class.
dilate: Dilates each channel independently.
dilate_rect_u8: Dilates a grayscale u8 image with a rectangular element in linear time.
dilate_rect_u8_into: Dilates into caller-owned packed output using reusable scratch storage.
disparity_to_depth: Converts horizontal disparity to metric depth with Z = f * B / d.
disparity_to_xyz: Reprojects disparity into left-camera XYZ using rectified intrinsics.
distance_transform_edt: Computes the exact Euclidean distance from every foreground pixel to the nearest background pixel using unit pixel spacing.
distance_transform_edt_into: Computes the exact unit-spacing Euclidean distance transform into a reusable slice.
distance_transform_edt_u8_into: Computes a unit-spacing exact distance transform from a packed u8 mask.
distance_transform_edt_with_spacing: Computes the exact Euclidean distance transform with physical pixel spacing.
encode_bytes: Encodes typed pixels into an owned byte vector.
encode_path: Creates or truncates a path and encodes typed pixels into it.
encode_rle: Encodes a binary mask into alternating runs.
encode_writer: Encodes typed pixels to a seekable writer.
equalize_histogram: Equalizes an 8-bit grayscale histogram.
erode: Erodes each channel independently.
erode_rect_u8: Erodes a grayscale u8 image with a rectangular element in linear time.
erode_rect_u8_into: Erodes into caller-owned packed output using reusable scratch storage.
estimate_and_stitch_panorama: Estimates a source-to-target homography and stitches the pair.
estimate_essential: Estimates an essential matrix after normalizing pixels with both cameras.
estimate_essential_ransac: Robustly estimates an essential matrix in normalized-camera coordinates.
estimate_fundamental: Estimates a fundamental matrix from at least eight correspondences.
estimate_fundamental_ransac: Robustly estimates a fundamental matrix using deterministic eight-point RANSAC.
estimate_homography: Estimates a homography from at least four correspondences using normalized DLT.
estimate_homography_ransac: Robustly estimates a homography using deterministic four-point RANSAC.
estimate_monocular_odometry: Estimates calibrated monocular motion with essential RANSAC and cheirality.
estimate_rgbd_odometry: Estimates metric motion from source depth and source-to-target pixel tracks.
estimate_rigid_transform: Estimates the rigid transform that best maps source onto target.
extract_indices: Extracts a sub-cloud containing only the selected point indices.
extract_mask: Extracts points where mask[index] is true.
f32_eps: Default tolerance for f32 comparisons.
f64_eps: Default tolerance for f64 comparisons.
filter2d: Applies OpenCV-style correlation and converts the result back to the input dtype.
filter2d_f32: Applies OpenCV-style correlation and preserves signed/fractional results as f32.
find_contours: Extracts oriented boundary loops, including hole contours.
fpfh_descriptors: Computes an FPFH descriptor for every point in cloud.
fuse_exposures: Fuses aligned RGB exposures with normalized per-pixel well-exposedness.
gaussian_blur: Applies a separable Gaussian blur with explicit odd sizes and standard deviations.
gaussian_blur_u8: Applies a specialized 3×3, 5×5, or 7×7 Gaussian blur to interleaved u8 input.
gaussian_blur_u8_into: Applies the specialized u8 Gaussian blur into caller-owned packed output and workspace.
gray_to_rgb: Replicates a gray channel into RGB.
gray_world_white_balance: Applies deterministic gray-world white balance to an RGB image.
harris_response: Computes an unnormalized Harris structure-tensor response image.
hausdorff_distance: Symmetric Hausdorff distance between two clouds (the largest NN distance in either direction). Captures the worst-case discrepancy.
histogram: Computes a configurable one-channel histogram, optionally through a mask.
histogram_u8: Computes the exact 256-bin histogram of an 8-bit grayscale image.
integral_image: Computes a summed-area table for one selected channel.
knn_graph: Builds a directed k-nearest-neighbor graph: an edge from every point to each of its k nearest neighbors (excluding itself).
laplacian: Computes a Laplacian response as signed f32 values.
letterbox: Aspect-preserving resize followed by centered constant padding.
match_descriptors: Matches each query descriptor to its nearest train descriptor.
median_blur: Applies a per-channel median filter with an odd square aperture.
merge_clouds: Concatenates clouds that share an identical schema into one cloud.
morphology_ex: Applies a composite morphology operation.
morphology_rect_u8: Applies composite grayscale u8 morphology using the rectangular fast path.
morphology_rect_u8_into: Applies composite rectangular morphology into caller-owned packed output.
nearest_k_spatial_tensor: Runs k-NN search for every chunk in a SpatialTensor, appending tagged neighbors.
nearest_k_spatial_tensor_parallel: Parallel k-NN search over SpatialTensor chunks.
nearest_k_spatial_tensor_parallel_into: Parallel k-NN search, appending (query_index, neighbor) pairs to out.
nms: Greedy non-maximum suppression. Returned indices are score-descending.
normalize: Converts packed scalar values to f32, then applies value * scale, mean subtraction, and per-channel standard-deviation normalization.
normalize_into: Normalizes interleaved pixels into caller-owned f32 storage.
normalize_unit_sphere: Recenters a cloud and scales it so its farthest point is at unit distance — the canonical normalization for learned point-cloud models.
orient_normal_towards_viewpoint: Orients a normal to point towards the viewpoint when possible.
orient_normals_consistent: Re-orients a cloud’s normals so neighboring normals agree in sign.
oriented_bounding_box: Oriented bounding box via principal component analysis of the positions.
otsu_threshold_u8: Selects an Otsu threshold for an 8-bit grayscale image and applies it.
otsu_threshold_u16: Selects an Otsu threshold for a 16-bit grayscale image and applies it.
pack_chw: Packs and normalizes an interleaved image into planar CHW storage.
pack_chw_into: Packs and normalizes interleaved pixels into a reusable planar CHW slice.
pad: Pads an image with a constant pixel value.
parallel_index_for_each: Runs work over disjoint index ranges using parallel_worker_count.
parallel_index_ranges: Returns disjoint half-open index ranges covering [0, point_count).
parallel_worker_count: Returns the number of worker threads to use for point_count points.
planar_f32_to_nchw: Packs a planar CHW f32 image into contiguous NCHW [1,C,H,W].
point_map_to_point_cloud: Flattens valid point-map pixels into an XYZ cloud, optionally filtering by confidence.
project_object_point: Projects an object point with an absolute pose into pixel coordinates.
pyr_down: Reduces each dimension by approximately two using the canonical 5×5 kernel.
pyr_up: Doubles each dimension using zero insertion and the canonical 5×5 kernel.
radius_graph: Builds a directed radius graph: an edge from every point to each other point within radius.
radius_search_spatial_tensor: Runs radius search for every chunk in a SpatialTensor, appending tagged neighbors.
radius_search_spatial_tensor_parallel: Parallel radius search over SpatialTensor chunks.
radius_search_spatial_tensor_parallel_into: Parallel radius search, appending (query_index, neighbor) pairs to out.
range_image: Projects a cloud into a spherical range image, keeping the nearest range per pixel. Points outside the vertical field of view are dropped.
read_copc: Reads all points from a COPC file on disk.
read_copc_file: Reads all points from a COPC file on disk.
read_copc_file_in_bounds: Reads points inside a bounding box at full available detail.
read_copc_file_info: Reads COPC header metadata without loading points.
read_copc_file_with_query: Reads points using a spatial bounds and optional LOD limit.
read_copc_url: Reads all points from a remote COPC URL.
read_copc_url_info: Reads COPC header metadata from a remote URL without loading points.
read_copc_url_with_query: Reads points from a remote COPC URL using an optional spatial query.
read_e57: Reads all scans from an E57 file and merges them into one point cloud.
read_e57_file: Reads all scans from an E57 file and merges them into one point cloud.
read_las: Reads a complete LAS/LAZ stream.
read_las_file: Reads a LAS/LAZ file from disk.
read_pcd: Reads a complete PCD file from any buffered reader.
read_pcd_file: Reads a PCD file from disk.
read_ply: Reads a complete PLY file from any buffered reader.
read_ply_file: Reads a PLY file from disk.
read_point_cloud_file: Reads a point cloud from disk, dispatching on the file extension.
read_point_cloud_file_with_format: Reads a point cloud using an explicit format.
recenter: Translates a cloud so its centroid sits at the origin.
recover_relative_pose: Recovers the essential-matrix pose with the most positive-depth points.
reduce_positions: Consumes a source and computes bounds and centroid without retaining chunks.
remap: Samples an image at absolute coordinates supplied by two single-channel maps.
resize: Resizes an interleaved image while preserving semantic metadata.
resize_into: Resizes into caller-owned storage without allocating.
resize_pack_chw: Fuses bilinear RGB resize, normalization, and CHW packing without an intermediate image.
resize_pack_chw_into: Fuses bilinear RGB resize, normalization, and CHW packing into caller-owned storage.
resize_rgb_to_gray: Fuses bilinear RGB resize and BT.601 grayscale conversion without an intermediate RGB image.
resize_rgb_to_gray_into: Fuses bilinear RGB resize and BT.601 grayscale conversion into caller-owned storage.
rgb_to_gray: Converts RGB u8 pixels to BT.601 luma using fixed-point coefficients.
rgb_to_gray_into: Converts RGB u8 pixels into caller-owned gray storage without allocating.
rgb_to_hsv: Converts RGB u8 to OpenCV-style HSV (H in 0..=179, S/V in 0..=255).
rgb_u8_to_nchw_f32: Letterboxes an RGB u8 image and packs it as contiguous NCHW f32 [1,3,H,W].
rgbd_to_point_cloud: Converts aligned RGB and depth images into an XYZRGB point cloud.
scale_cloud: Uniformly scales a cloud about the origin by factor.
scharr: Computes a 3×3 Scharr first derivative as signed f32 values.
score_tensor_to_binary_mask: Converts a host score tensor into a binary mask via threshold.
select_keypoints_grid: Retains the strongest keypoints in each image cell.
separable_filter: Applies horizontal and vertical kernels using an f64 intermediate buffer.
separable_filter_f32: Applies separable kernels and preserves signed/fractional output as f32.
shi_tomasi_response: Computes an unnormalized Shi–Tomasi minimum-eigenvalue response image.
smallest_eigenvector: Returns the eigenvector for the smallest eigenvalue.
sobel: Computes a Sobel derivative as signed f32 values.
sobel_3x3_u8: Computes a first-order 3x3 Sobel derivative directly into signed f32 output.
sobel_3x3_u8_into: Computes a first-order 3x3 Sobel derivative into caller-owned packed output.
sobel_abs_3x3_u8: Computes an exact absolute first-order 3x3 Sobel response as saturated u8.
sobel_abs_3x3_u8_into: Computes an exact absolute first-order 3x3 Sobel response into packed output.
sobel_l1_magnitude_u8: Computes exact 3×3 Sobel L1 magnitude (|Gx| + |Gy|) for grayscale u8.
sobel_l1_magnitude_u8_into: Computes exact fused 3×3 Sobel L1 magnitude into caller-owned packed output.
sobel_threshold_3x3_u8: Computes a binary edge mask from absolute 3x3 Sobel response.
sobel_threshold_3x3_u8_into: Computes a binary absolute-Sobel edge mask into caller-owned packed output.
soft_nms: Soft non-maximum suppression with deterministic score ordering.
solve_linear_system: Solves A x = b for square n x n systems using Gaussian elimination with partial pivoting.
solve_pnp: Estimates an object-to-camera pose from at least four correspondences.
solve_pnp_ransac: Robust PnP using deterministic six-point RANSAC and inlier refinement.
spatial_gradient_u8: Computes exact 3×3 Sobel X/Y gradients together for grayscale u8 input.
spatial_gradient_u8_into: Computes exact paired 3×3 Sobel gradients into caller-owned packed output.
stereo_block_match: Dense SAD block matching on already-rectified grayscale stereo images.
stereo_rectify: Builds left/right absolute remap grids that make epipolar lines horizontal.
stitch_panorama_pair: Warps source into target coordinates and feather-blends their overlap.
swap_red_blue: Swaps the red and blue channels of a three-channel image.
symmetric_eigen3: Computes eigenvalues and eigenvectors of a symmetric 3x3 matrix.
threshold: Applies a fixed threshold independently to every component.
track_points_forward_backward: Tracks points in both directions and rejects inconsistent round trips.
track_points_lucas_kanade: Tracks sparse points from previous to next with pyramidal Lucas–Kanade.
transform_point_cloud: Applies a rigid transform to point positions and normals in a point cloud copy.
triangulate_correspondence: Triangulates one calibrated correspondence for a known relative pose.
voxelize: Voxelizes a cloud into a dense occupancy / count grid.
warp_affine: Warps an image with a source-to-destination affine transform.
warp_perspective: Warps an image with a source-to-destination projective transform.
with_labels: Adds or replaces a per-point label field on a point cloud copy.
write_copc: Writes a point cloud to a COPC file on disk.
write_copc_file: Writes a point cloud to a COPC file on disk.
write_copc_file_with_params: Writes a point cloud to a COPC file using custom octree builder parameters.
write_e57: Writes a point cloud to an E57 file on disk.
write_e57_file: Writes a point cloud to an E57 file on disk.
write_las: Writes a point cloud to a LAS/LAZ stream and returns the inner writer.
write_las_file: Writes a point cloud to a LAS/LAZ file on disk.
write_pcd: Writes a point cloud to a PCD stream.
write_pcd_file: Writes a point cloud to a PCD file on disk.
write_ply: Writes a point cloud to a PLY stream.
write_ply_file: Writes a point cloud to a PLY file on disk.
write_point_cloud_file: Writes a point cloud to disk, dispatching on the file extension.
write_point_cloud_file_with_format: Writes a point cloud using an explicit format.

Type Aliases§

ChunkQueryRange: Range of query point indices (matches SpatialTensor::chunks ranges).
FpfhDescriptor: A single FPFH descriptor.
GrayImage: A one-channel image.
RgbImage: A three-channel RGB image.
SpatialResult: Result type used across SpatialRust crates.
VisionResult: Result type for image and vision operations.

Crate spatialrust

Crate spatialrust Copy item path

Re-exports§

Structs§

Enums§

Constants§

Traits§

Functions§

Type Aliases§

Crate spatialrust