compute_fpfh — 3D feature_register op

• Data kinds: points × normals → descriptor

• Call: import feat_fpfh; feat_fpfh.compute_fpfh(points, normals, k=60, n_bins=11) (or ops3d.get("compute_fpfh"))

Usage

Compute the FPFH descriptor (N, 3*n_bins) (Rusu 2009).

Background guides (the physics and conventions behind this op)

• blas_threads_and_memory — 行列分解が遅い理由の知識 — BLAS スレッド・キャッシュ・メモリ配置

References (sample data, literature)

• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).

• Operator provenance and references — the sources of the research/methods this op family came from.

Runnable examples (verified samples that actually call this op)

• fpfh_correspondence — py -3.11 examples_3d/fpfh_correspondence.py

Ops the type connects to (they accept descriptor as input)

fuse_to_voxel · shape_distance

Same category (feature_register)

harris3d_keypoints · iss_keypoints · shot_descriptor · register_spin · register_fpfh · register_shot

*Provenance: feat_fpfh.py — 3D operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*

© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.