d2_distribution — 3D shape_descriptor op

Data kinds: pointsdescriptor

Call: import fullseye as fs; fs.ledger.d2_distribution(points, bins: 'int' = 64, samples: 'int' = 100000, seed: 'int' = 0) -> 'np.ndarray' (to call the implementation directly, import descriptors3d; descriptors3d.d2_distribution(points, bins: 'int' = 64, samples: 'int' = 100000, seed: 'int' = 0) -> 'np.ndarray'; from the registry, ops3d.get("d2_distribution"))

Usage

The distribution of Euclidean distances between random point pairs (Osada 2002's D2).

> The detailed description below is the original text — the summary and the headings are translated.

N 点から samples 組の相異なる点対 (i, j) を乱択し、その距離を集計する。

距離は平均距離で割って正規化するため、回転・平行移動・スケールに不変。

固定レンジ [0, _D2_MAX] の正規化ヒストグラム (bins,) を返す(総和 1)。

Parameters

----------

points : array_like, shape (N, 3)

点群。N >= 2 が必要。

bins : int

ヒストグラムの bin 数。

samples : int

乱択する点対の数。多いほど分散が下がる(サンプリング誤差 ~ 1/sqrt(samples))。

seed : int

乱数シード。同 seed・同点群なら決定論的に同一。

Returns

-------

np.ndarray, shape (bins,)

正規化距離ヒストグラム。

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)

shape_desc_posepy -3.11 examples_3d/shape_desc_pose.py

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

fuse_to_voxel · shape_distance

Same category (shape_descriptor)

a3_distribution · extent_signature · describe · shape_distance


*Provenance: descriptors3d.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.