Capability map

Algorithm catalog

Find an algorithm by task, then follow its crate link to the generated API. Entries describe implemented public families, not future intentions.

AreaAlgorithms and operationsRust crate / featureBackend
FilteringPass-through, crop box, voxel-grid downsample, statistical/radius outlier removal, farthest-point sampling, moving least squaresspatialrust-filteringCPU
Spatial searchBrute force, k-d tree, radius/k-nearest queries, chunked parallel queries, uniform grid, k-NN/radius neighbor graphsspatialrust-searchCPU
Point featuresNormal estimation and orientation, ISS keypoints, boundary detection, FPFH descriptorsspatialrust-features, registrationCPU / GPU
SegmentationRANSAC plane/sphere/cylinder, multi-plane, ground, Euclidean clustering, DBSCAN, region growingspatialrust-segmentationCPU / GPU
RegistrationRigid Kabsch, point-to-point ICP, point-to-plane ICP, GICP, NDT, FPFH+RANSAC global alignmentspatialrust-registrationCPU
VoxelizationOccupancy grids, range images, voxel keys, segments, centroid/first-point reductionsspatialrust-voxelize, gpuCPU / GPU
TransformsApply transform, centroid, AABB/OBB, recenter, scale, unit-sphere normalization, mergespatialrust-transformCPU
PreprocessingCrop, pad, letterbox, normalize, interleaved-to-CHW, RGB/BGR swap, RGB↔gray/HSV, reusable outputs. Fused bilinear resize-to-gray avoids an intermediate RGB image and wins 1.12× at allocated 1080p→540p. Fused resize-normalize-CHW avoids the HWC intermediate and measured 2.02×–2.33× faster than OpenCV blobFromImage. Both retain exact SpatialRust unfused parity. CHW harness.spatialrust-vision · preprocessCPU
Resize and warpNearest, bilinear, bicubic and area resize; reusable fixed-point RGB8 bilinear plans; exact row-parallel half-scale path; remap; affine and perspective warp. VGA caller-output half-scale measured 1.10× faster than OpenCV with exact pixels. Harness.spatialrust-vision · resize, warpCPU / GPU
Filtering2D correlation/convolution, separable/box/Gaussian, accelerated 3×3/5×5 u8 Gaussian, median, bilateral, direct 3×3 Sobel, exact paired gradients, fused absolute/binary Sobel responses and L1 magnitude, Scharr, Laplacian, Gaussian pyramids. Exact direct Sobel beats OpenCV 1.88× at 1080p and 2.03× at 4K; fused threshold masks win 2.95×–8.68× depending on allocation mode. Harness.spatialrust-vision · imgproc-filtersafe CPU explicit GPU API
MorphologyErode, dilate, open, close, gradient, top-hat, black-hat; separable sliding Rect fast path plus Cross/Ellipse/Diamond/custom fallbackspatialrust-vision · imgproc-morphologysafe CPU explicit wgpu API
Image analysisFixed/Otsu/adaptive threshold, histogram, equalization, CLAHE, integral image, Cannyspatialrust-vision · imgproc-analysis, imgproc-cannyCPU
Local featuresFAST, Harris, Shi–Tomasi, ORB, descriptor matching, grid selection, pyramidal Lucas–Kanade trackingspatialrust-vision · feature2dCPU
Dense visionExact Euclidean distance transform with reusable workspace/output; allocation-light Canny with opt-in inspectable intermediates; row-major run-length/union-find connected components; contours, polygon approximation, mask RLE, and dense spatial maps. Canny uses parallel three-row magnitude rings, safe strided output, and reusable workspace with bit-exact OpenCV parity across 300 randomized images. Reusable document-line Canny measured 1.36× faster than OpenCV at 1080p and 1.42× at 4K; dense sensor noise remains an OpenCV win. Canny harness. Structured connected-component masks measured 2.17×–3.61× faster than OpenCV SAUF. Components harness.spatialrust-vision · denseCPU
Detection post-processingIoU/GIoU, greedy NMS, class-aware batched NMS, and hard/linear/Gaussian Soft-NMS. Seeded Python NMS is 3.22×–8.95× faster than OpenCV; batched NMS is 26.38×–97.25× faster; linear/Gaussian Soft-NMS is 3.42×–7.40× faster. NMS indices are exact and Soft-NMS scores stay within 1.79e-7. NMS · batched · Soft-NMS.spatialrust-vision · detectionCPU
Multiview geometryHomography, fundamental/essential matrices, RANSAC, triangulation, relative pose, PnP/PnP-RANSACspatialrust-vision · geometryCPU
Stereo and odometryStereo rectification, block matching, disparity-to-depth/XYZ, monocular and RGB-D visual odometryspatialrust-vision · geometry, odometryCPU
VideoDense block flow, adaptive background model, multi-object tracker, timestamped pull sourcesspatialrust-vision · videoCPU
PhotographyGray-world white balance, exposure fusion, bounded panorama estimation, warp and feather stitchingspatialrust-vision · photographyCPU
Camera and RGB-DPinhole/fisheye projection and distortion, mono/stereo/hand-eye calibration, point bundle adjustment, depth-to-XYZ/point-cloudspatialrust-cameraCPU
MappingStamped trajectories, delta motion, visual-odometry bridge, pose-graph construction, root localization, and loop-closure candidatesspatialrust-mappingCPU
Scene reconstructionTSDF integration, marching cubes, surfel fusion, CPU Gaussian splat rendering, triangle meshesspatialrust-sceneCPU / GPU features
Semantic spatialEmbeddings, cosine similarity, multimodal fusion, semantic search index, open-vocabulary entitiesspatialrust-semanticCPU
GPU computeExplicit image upload/readback, device-resident copy/gray/blur/resize/Sobel/morphology, voxel reduction, normals, clustering, plane scoringspatialrust-gpuwgpu
AI and tensorsImage↔tensor packing, DLPack import/export, backend/session contracts, mock inference and optional ONNX Runtimespatialrust-tensor, aiCPU / optional runtime
Execution and distributionTyped DAG compilation, same-device fusion, bounded backpressure, partitioning, named transfers and transfer ledgersspatialrust-runtime, distributeExplicit placement
Time and replayClock domains, frame graphs, deterministic multimodal replay, MCAP episode round-tripspatialrust-syncCPU / optional I/O

Feature names describe Cargo gates on the algorithm crate. Exact signatures and stability are authoritative in rustdoc and API_STABILITY.md. GPU entries always require explicit device APIs.