harris3d_keypoints — 3D feature_register op

• Data kinds: voxel → keypoints

• Call: import feat_harris; feat_harris.harris3d_keypoints(vol, device='cpu', k=0.005, nms=3, topn=64, sigma_i=1.5, response='mineig', rel_thresh=0.01, border=2) (or ops3d.get("harris3d_keypoints"))

• GPU: this op has a GPU path (device="cuda")

Usage

3-D Harris keypoint detection (the 3-D version of the 2-D Harris corner detector).

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)

• feature_register — py -3.11 examples_3d/feature_register.py

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

fuse_to_voxel · dlt_pose · pnp_ransac · reprojection_error

Same category (feature_register)

iss_keypoints · compute_fpfh · shot_descriptor · register_spin · register_fpfh · register_shot

*Provenance: feat_harris.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.